© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58936
    Prev
    Next
    INDEX
    Explanations

    variations of the word "the" and its interactions in sentences

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

    their own, or possessive phrases

    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
     Nutzungs
    -0.35
    tonode
    -0.35
     modernas
    -0.33
    허
    -0.33
     roja
    -0.32
     Bohn
    -0.30
    tagHelperRunner
    -0.30
     Maddox
    -0.29
     Aufenthalt
    -0.29
     ویکی‌پدیای
    -0.28
    POSITIVE LOGITS
    ScopeManager
    0.67
    providedIn
    0.61
    脚注の使い方
    0.57
    RectangleBorder
    0.53
     تضيفلها
    0.53
    rror
    0.52
     AttributeSet
    0.51
    ANTLR
    0.49
    ntag
    0.48
    IBinder
    0.48
    Activations Density 0.041%

    No Known Activations