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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70284
    Prev
    Next
    INDEX
    Explanations

    significant themes related to personal growth and self-improvement through creative expression

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

    regulating biological processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tercih
    -0.37
    kwds
    -0.36
    bahasan
    -0.34
    staticmethod
    -0.34
    页面存档备份
    -0.33
    ereich
    -0.30
     ReSharper
    -0.30
    ोंने
    -0.30
    клопе
    -0.29
     Finger
    -0.29
    POSITIVE LOGITS
    новништво
    0.69
    MessageOf
    0.64
    ſelf
    0.63
     poffible
    0.58
     itſelf
    0.58
    ValueStyle
    0.57
    UIControlState
    0.56
     $_(
    0.55
    phite
    0.54
    OGND
    0.54
    Activations Density 0.110%

    No Known Activations