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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 9969
    Prev
    Next
    INDEX
    Explanations

    expressions of recommendation and positive evaluation

    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
    LLocation
    -0.68
    ScopeManager
    -0.63
     resourceCulture
    -0.61
     InputDecoration
    -0.56
    matchCondition
    -0.54
    EndContext
    -0.54
    MessageOf
    -0.54
    sizeCache
    -0.54
    encodeWith
    -0.50
    VolleyError
    -0.49
    POSITIVE LOGITS
     Highly
    1.03
     highly
    0.96
    Highly
    0.95
    highly
    0.86
     recommend
    0.84
     Definitely
    0.83
     Recommend
    0.82
     Recommended
    0.81
     definitely
    0.77
     worth
    0.76
    Activations Density 0.094%

    No Known Activations