© 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. 9-GEMMASCOPE-RES-131K
    11. 58671
    Prev
    Next
    INDEX
    Explanations

    references to specific characters and locations in video games

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

    legend of shrine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scattata
    -0.28
     Yes
    -0.27
     Mea
    -0.24
     themselves
    -0.24
     himself
    -0.23
     PI
    -0.23
     Kab
    -0.23
     sur
    -0.23
     zaj
    -0.23
     kompeti
    -0.22
    POSITIVE LOGITS
    mybatisplus
    0.85
    providedIn
    0.68
    出版年
    0.65
    carina
    0.64
    enumii
    0.64
    exitRule
    0.62
     חיצוניים
    0.60
     surla
    0.60
    tinyos
    0.60
    Xna
    0.60
    Activations Density 0.009%

    No Known Activations