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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7770
    Prev
    Next
    INDEX
    Explanations

    historical references and significant places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     venezolano
    -0.51
     dinámico
    -0.46
     calcetines
    -0.44
     rechange
    -0.44
     Parisian
    -0.43
     Latinoamérica
    -0.43
     Schäfer
    -0.43
     adecuadamente
    -0.43
     Egipto
    -0.42
     Polri
    -0.42
    POSITIVE LOGITS
     Port
    0.75
     Mount
    0.72
     West
    0.72
     East
    0.71
     North
    0.71
     Mt
    0.70
     South
    0.69
     Lake
    0.69
     Oak
    0.67
     Milford
    0.63
    Activations Density 1.092%

    No Known Activations