© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57516
    Prev
    Next
    INDEX
    Explanations

    exclamatory expressions of surprise or realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.84
     ―――――
    -0.82
     roy
    -0.78
    fifths
    -0.75
    ——-
    -0.75
    BoxShadow
    -0.74
     iſt
    -0.73
     Conſ
    -0.73
     RIV
    -0.72
     itſelf
    -0.72
    POSITIVE LOGITS
     Ah
    1.30
     ah
    1.22
    Ah
    1.10
     AH
    1.05
    ah
    0.97
     Ahmet
    0.94
    AH
    0.92
     Ahh
    0.86
    Ahh
    0.84
     Gump
    0.81
    Activations Density 0.012%

    No Known Activations