© 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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 516
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structure definitions and database operations

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

    Followed by curly braces or brackets

    np_acts-logits-general · gemini-2.0-flash

    following, suivantes, folgende

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.70
     utafitiHapana
    -0.65
    ⟬
    -0.62
     MainAxisSize
    -0.59
    Tikang
    -0.58
    zzleHttp
    -0.57
    MLLoader
    -0.57
    ReusableCell
    -0.56
    ViewImports
    -0.56
    posedge
    -0.55
    POSITIVE LOGITS
    "}},
    0.45
    setVerticalGroup
    0.45
     following
    0.44
    '}}>
    0.40
    Бахар
    0.36
     suivantes
    0.36
    ":[
    0.36
    '}>
    0.35
    })}\
    0.34
     folgende
    0.34
    Activations Density 0.436%

    No Known Activations