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. 9687
    Prev
    Next
    INDEX
    Explanations

    language related to injustices and societal issues

    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
    ActionCreators
    -0.72
     demurrer
    -0.60
     efficacité
    -0.54
     QtGui
    -0.54
     isInitialized
    -0.53
    endaft
    -0.52
    contentLoaded
    -0.52
    dalena
    -0.52
     QtWidgets
    -0.51
    jelder
    -0.51
    POSITIVE LOGITS
     like
    0.55
     ProtoMessage
    0.53
    '&:
    0.51
    ASF
    0.49
    flik
    0.48
     otomatig
    0.48
    eiras
    0.48
    WebElementEntity
    0.47
     nor
    0.46
     likes
    0.46
    Activations Density 0.499%

    No Known Activations