© 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. 0-GEMMASCOPE-RES-65K
    6. 9878
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "rib" and terms related to hip dislocation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.67
     Lesotho
    -0.67
    endgroup
    -0.61
     stø
    -0.60
    MENAFN
    -0.59
    Vist
    -0.57
    աց
    -0.57
    esgue
    -0.56
    underland
    -0.55
    ksikon
    -0.55
    POSITIVE LOGITS
     Hip
    0.91
    hip
    0.89
     hip
    0.87
    IsContent
    0.85
     mad
    0.79
    Hip
    0.78
    mad
    0.75
    rico
    0.69
     Rib
    0.68
     rib
    0.68
    Activations Density 0.032%

    No Known Activations