© 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. 7-GEMMASCOPE-RES-16K
    11. 14112
    Prev
    Next
    INDEX
    Explanations

    instances of the word "affect" and its variations, indicating a focus on the influence or impact of events, conditions, or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteLiteral
    -0.36
     مجه
    -0.32
    espa
    -0.32
    rieux
    -0.31
    unzi
    -0.30
     flipped
    -0.30
    ிறது
    -0.30
     acesta
    -0.30
    هرست
    -0.30
    ereum
    -0.30
    POSITIVE LOGITS
     affected
    2.17
     Affected
    2.03
    affected
    1.92
    Affected
    1.87
     affecting
    1.82
     affect
    1.76
     AFFECT
    1.75
     affects
    1.71
    affect
    1.70
     Affecting
    1.63
    Activations Density 0.194%

    No Known Activations