© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9335
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to studies or formulations

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

    scientific or technical terms in specialized texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     ujednoznacz
    -0.69
     <<<<<<<<<<<<<<
    -0.65
    ropriate
    -0.60
     Walkover
    -0.59
    saco
    -0.57
    Бахар
    -0.55
    identiality
    -0.54
     متعلقه
    -0.54
     nahilalakip
    -0.54
     Slate
    -0.53
    POSITIVE LOGITS
     also
    0.42
     тоже
    0.39
     likewise
    0.37
     също
    0.36
     też
    0.36
     tampoco
    0.35
    ก็
    0.33
     också
    0.33
     también
    0.32
     نیز
    0.31
    Activations Density 0.688%

    No Known Activations