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
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8652
    Prev
    Next
    INDEX
    Explanations

    phrases related to mathematical operations or expressions involving prime factors and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    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
    -0.75
     HasFactory
    -0.49
    󠁿
    -0.48
    ScopeManager
    -0.47
    ItemBackground
    -0.47
     BorderSide
    -0.46
     يتيمه
    -0.46
    awaiter
    -0.45
    RenderAtEndOf
    -0.45
    MigrationBuilder
    -0.45
    POSITIVE LOGITS
     p
    2.59
     P
    2.47
    P
    1.91
    p
    1.88
     getP
    1.63
    setP
    1.53
    getP
    1.46
     پ
    1.44
    p
    1.32
     п
    1.24
    Activations Density 3.568%

    No Known Activations