© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 44224
    Prev
    Next
    INDEX
    Explanations

    blocks of code or marked sections in programming or documentation

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

    public class

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    InjectAttribute
    -0.53
    
    -0.47
    Климаты
    -0.46
     nahilalakip
    -0.45
    lamda
    -0.44
    ViewFeatures
    -0.43
    ActionCreators
    -0.43
    求
    -0.43
    Controllo
    -0.42
    ucid
    -0.41
    POSITIVE LOGITS
     static
    0.54
    static
    0.51
    MessageOf
    0.50
    XmlAccessorType
    0.43
     parseFrom
    0.40
    :✨
    0.40
    futbolista
    0.39
     تضيفلها
    0.37
    companion
    0.37
     proyek
    0.37
    Activations Density 0.005%

    No Known Activations