© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6185
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operators typically used in equations and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions with index subscripts and superscripts, particularly those with indices i+1, i-1, or j+1.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    mathematical operators and symbols that connect variables with addition or subtraction in equations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.76
     يتيمه
    -0.67
    帖最后由
    -0.63
    MigrationBuilder
    -0.57
    KommentareTeilen
    -0.56
    __*/
    -0.55
     Италијани
    -0.55
     мәкал
    -0.55
    })();
    -0.55
     nahilalakip
    -0.54
    POSITIVE LOGITS
    1
    0.37
     one
    0.36
    անի
    0.35
    ashing
    0.34
    gion
    0.34
    projec
    0.33
    itatis
    0.33
    othelioma
    0.33
     capilla
    0.32
    thin
    0.31
    Activations Density 0.734%

    No Known Activations