© 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. 38654
    Prev
    Next
    INDEX
    Explanations

    the presence of coding or programming structures, particularly those related to object initialization and functional definitions

    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
     fullt
    -0.82
    Hochspringen
    -0.80
     Rosenberg
    -0.75
     Garfield
    -0.73
     لينك
    -0.69
     Sandberg
    -0.69
     nakalista
    -0.69
    bicara
    -0.66
    Cyfeiriadau
    -0.66
     oog
    -0.66
    POSITIVE LOGITS
     Rima
    0.91
     Esther
    0.89
     BIB
    0.86
     Umbrella
    0.84
    qin
    0.83
     Jab
    0.83
     Hoo
    0.82
     Cauliflower
    0.79
     Vaz
    0.79
     oes
    0.77
    Activations Density 0.038%

    No Known Activations