© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 91142
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure definitions and codes

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

    bundle name or direct action

    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
    Latch
    -0.52
    ulemon
    -0.46
    ArgsConstructor
    -0.45
    BeginInit
    -0.45
     emitir
    -0.45
     âmes
    -0.44
    KommentareTeilen
    -0.43
    Diwedd
    -0.43
    Magic
    -0.43
    ########.
    -0.42
    POSITIVE LOGITS
    Chunks
    0.52
    μιουργ
    0.39
     chunks
    0.37
    adaptiveStyles
    0.35
    WebElementEntity
    0.34
     Zustimmung
    0.34
     Kriterien
    0.34
    chunks
    0.33
     obserw
    0.33
     splitting
    0.33
    Activations Density 0.001%

    No Known Activations