Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15291
    Prev
    Next
    INDEX
    Explanations

    instances of high-value assertions or statements

    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
     lemmas
    -0.59
    ValueStyle
    -0.59
    ---*/
    -0.58
     virginity
    -0.57
     CCP
    -0.55
     Benzema
    -0.54
    saga
    -0.53
    ppets
    -0.53
    tsd
    -0.53
     Dabei
    -0.53
    POSITIVE LOGITS
    WriteBarrier
    0.72
     WaitForSeconds
    0.71
     you
    0.63
     the
    0.60
     everyone
    0.59
     it
    0.58
     your
    0.57
    Tembelea
    0.57
    )");
    
    0.57
     we
    0.56
    Activations Density 0.053%

    No Known Activations