© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8472
    Prev
    Next
    INDEX
    Explanations

    variable declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 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
    ValueStyle
    -0.77
     InputDecoration
    -0.73
     ProtoMessage
    -0.69
    kuuta
    -0.68
    Tembelea
    -0.67
    ########.
    -0.65
    enumi
    -0.63
    MessageInfo
    -0.62
    الإنجليزية
    -0.62
     Partagez
    -0.61
    POSITIVE LOGITS
    let
    0.55
    іга
    0.51
    mste
    0.50
    NSMutable
    0.49
    bitField
    0.48
    writeHead
    0.47
    }{*}{
    0.46
    اهر
    0.45
    immer
    0.44
    endum
    0.44
    Activations Density 0.094%

    No Known Activations