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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5456
    Prev
    Next
    INDEX
    Explanations

    expressions of disappointment, concern, or condemnation regarding societal issues and injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ac
    -0.49
    ?
    -0.48
     
    -0.48
    ht
    -0.47
    switch
    -0.47
    AC
    -0.43
    llo
    -0.43
     $
    -0.43
    Ap
    -0.43
    var
    -0.43
    POSITIVE LOGITS
     Efq
    0.73
     Roskov
    0.72
     primaire
    0.71
     métallique
    0.70
     unacceptable
    0.67
     réglable
    0.66
    μως
    0.65
    AccessorTable
    0.65
     honte
    0.65
     Monfieur
    0.64
    Activations Density 0.211%

    No Known Activations