© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 44203
    Prev
    Next
    INDEX
    Explanations

    structured data entries or code-like syntax

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

    subsequent continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SourceChecksum
    -0.63
     nahilalakip
    -0.57
    WireFormatLite
    -0.56
    setupUi
    -0.53
    MultipartFile
    -0.52
    Portail
    -0.52
    osan
    -0.51
    tedly
    -0.50
    rikan
    -0.50
    WebElementEntity
    -0.49
    POSITIVE LOGITS
    seamnă
    0.48
     poffible
    0.46
     mensuales
    0.43
     Daarna
    0.41
    enumi
    0.41
     vervolgens
    0.40
    escalier
    0.40
     Selanjutnya
    0.39
     Thereafter
    0.38
     hidráulica
    0.38
    Activations Density 0.105%

    No Known Activations