Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 109
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and connections between concepts

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

    scientific or statistical language related to complex processes and measurements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    waffe
    -0.41
    épendance
    -0.39
     biet
    -0.37
    roek
    -0.37
     Ters
    -0.37
     nader
    -0.36
    uebas
    -0.36
     dioxide
    -0.36
    دانشنامهٔ
    -0.35
    awaiter
    -0.34
    POSITIVE LOGITS
     Likewise
    0.72
     similarly
    0.72
    Likewise
    0.71
     Similarly
    0.68
     same
    0.67
    Similarly
    0.66
    +#+#
    0.65
     Ebenso
    0.63
     likewise
    0.63
    Personensuche
    0.63
    Activations Density 0.202%

    No Known Activations