© 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. 5-GEMMASCOPE-RES-16K
    6. 9611
    Prev
    Next
    INDEX
    Explanations

    references to specific "pieces."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.84
    esercito
    -0.84
     ExecuteAsync
    -0.84
     Hald
    -0.82
    */;
    -0.82
    (!__
    -0.81
    ")));
    
    -0.81
    Cordialement
    -0.80
    "):
    
    -0.80
    خواندن
    -0.79
    POSITIVE LOGITS
     pieces
    2.29
     piece
    2.29
     Pieces
    2.18
     Piece
    2.17
    Pieces
    2.15
     PIECE
    2.11
    Piece
    2.05
    piece
    1.95
    pieces
    1.93
    PIECE
    1.52
    Activations Density 0.038%

    No Known Activations