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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15912
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to game objects and their properties in a programming or development context

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

    UnityEngine object or component

    np_acts-logits-general · gemini-2.0-flash

    Unity script components

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MENAFN
    -0.60
     surla
    -0.57
    ValueStyle
    -0.51
    EDEFAULT
    -0.50
    ilitary
    -0.44
    ftagPool
    -0.43
    GTCX
    -0.43
    hyrchwyd
    -0.43
    protoimpl
    -0.43
     isoto
    -0.42
    POSITIVE LOGITS
     component
    0.89
     Component
    0.75
     components
    0.71
     GetComponent
    0.68
     componente
    0.68
    component
    0.68
     MonoBehaviour
    0.65
    Component
    0.65
     script
    0.65
     transform
    0.63
    Activations Density 0.057%

    No Known Activations