© 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. 7-GEMMASCOPE-RES-16K
    6. 14724
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those associated with API requests and data handling

    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
     heet
    -0.34
    chest
    -0.33
     B
    -0.32
    ocrine
    -0.31
    making
    -0.30
    OGND
    -0.30
    ọi
    -0.30
     hy
    -0.29
    क्त
    -0.28
    ofstream
    -0.28
    POSITIVE LOGITS
    Aiheesta
    0.69
     nahilalakip
    0.63
     AssemblyCulture
    0.61
    󠁢
    0.60
     pinulongan
    0.60
    /*
    0.59
    ricians
    0.55
    LookAnd
    0.54
     defaultstate
    0.54
     parachoque
    0.53
    Activations Density 0.396%

    No Known Activations