Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 88738
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and numerical values

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

    peace deals and treaties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.67
     الحره
    -0.65
     ProtoMessage
    -0.62
    ✨:
    -0.59
    SharedDtor
    -0.58
     '{@
    -0.57
    extAlignment
    -0.56
    StoreMessageInfo
    -0.56
    ThroughAttribute
    -0.55
    UnusedPrivate
    -0.54
    POSITIVE LOGITS
    Captured
    0.38
     secretos
    0.31
    PROLOG
    0.31
     prins
    0.30
     tuer
    0.30
     secreto
    0.29
     gráficos
    0.29
     meurt
    0.28
     wings
    0.28
     centros
    0.28
    Activations Density 0.101%

    No Known Activations