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. 24-GEMMASCOPE-RES-16K
    6. 1114
    Prev
    Next
    INDEX
    Explanations

    terms related to medical studies and clinical evaluations

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

    after scientific terms/measurements

    np_acts-logits-general · gemini-2.0-flash

    cirrhosis, rollers, GABA, fiber, Hybrid, interactions, parse, soft

    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
    IsContent
    -0.71
    HasAnnotation
    -0.68
    DockStyle
    -0.60
    adaptiveStyles
    -0.57
     ProtoMessage
    -0.55
     Numerade
    -0.55
    دانشنامهٔ
    -0.50
     ویکی‌پدی
    -0.50
    tangentMode
    -0.48
    RTSC
    -0.48
    POSITIVE LOGITS
     dAtA
    0.43
    GTCX
    0.42
    AnimationsModule
    0.41
    WRENCE
    0.38
     technological
    0.38
    </thead>
    0.37
     kuliner
    0.37
    EDEFAULT
    0.35
    beza
    0.35
    latego
    0.35
    Activations Density 1.446%

    No Known Activations