© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8772
    Prev
    Next
    INDEX
    Explanations

    patterns and structures related to programming syntax and data types

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

    type casting operations with parentheses.

    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
    }}/>
    -0.37
    ніципа
    -0.28
    TabLayout
    -0.28
    AddField
    -0.27
    getResultList
    -0.27
    ykjav
    -0.27
    {/
    -0.27
    '])->
    -0.26
    >;<
    -0.26
     contra
    -0.26
    POSITIVE LOGITS
    NameInMap
    0.65
    AnchorStyles
    0.62
     autorytatywna
    0.61
     فريبيس
    0.57
    eleste
    0.57
     kasarigan
    0.54
    ledes
    0.54
     članak
    0.52
     Drapeau
    0.52
     dovre
    0.50
    Activations Density 0.076%

    No Known Activations