© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5084
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express complexity and depth in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    meta-linguistic reflections about the difficulty of describing complex experiences or emotions using words.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    language about description and expression—mentions of “words,” describing or articulating something, especially highlighting difficulty or inadequacy in conveying it.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    expressions indicating difficulty or inability to adequately describe or express something in words.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.63
    ⓧ
    -0.60
    новниш
    -0.56
    proof
    -0.52
     Consult
    -0.50
    postsleuth
    -0.50
    Families
    -0.49
    Rebs
    -0.49
     Meksiku
    -0.49
     Families
    -0.48
    POSITIVE LOGITS
     وصف
    0.50
     describir
    0.50
     indescribable
    0.46
     describes
    0.46
     words
    0.46
     décrire
    0.45
     describing
    0.43
     description
    0.43
     décrit
    0.42
    AccessorTable
    0.42
    Activations Density 0.115%

    No Known Activations