© 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. 4-GEMMASCOPE-RES-16K
    11. 404
    Prev
    Next
    INDEX
    Explanations

    instances of introductory phrases typically used in mathematical or logical statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.74
     Grecian
    -0.74
    wiſe
    -0.73
    ſelf
    -0.72
     himſelf
    -0.72
     nargin
    -0.72
     للاسماء
    -0.71
    >')
    -0.70
    ;");
    -0.69
    ^(@)
    -0.68
    POSITIVE LOGITS
     Let
    1.68
    Let
    1.63
     LET
    1.35
     let
    1.15
    LET
    0.95
    let
    0.94
    Lets
    0.84
    Пусть
    0.78
     Lets
    0.75
     Пусть
    0.74
    Activations Density 0.184%

    No Known Activations