© 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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 3561
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns related to individuals or specific subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    紹介します
    -0.58
     św
    -0.57
    uasion
    -0.57
     tibi
    -0.54
     tubercle
    -0.54
     Dubuque
    -0.52
     sqlalchemy
    -0.51
     bogotá
    -0.50
     Shasta
    -0.49
     uuid
    -0.49
    POSITIVE LOGITS
     midst
    0.94
    httphttps
    0.86
    CloseOperation
    0.85
    Nella
    0.80
    :],
    0.77
    //</
    0.75
     Nella
    0.74
    脚注の使い方
    0.74
    --
    
    0.73
     vicinity
    0.73
    Activations Density 0.137%

    No Known Activations