© 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8771
    Prev
    Next
    INDEX
    Explanations

    references to a deity and protective prayers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onsored
    -0.63
    astr
    -0.48
    neurial
    -0.47
    WO
    -0.47
    avyzd
    -0.45
    toThrow
    -0.45
    Told
    -0.44
     νό
    -0.44
    outing
    -0.43
     деле
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.91
     Amen
    0.83
    parsedMessage
    0.78
    Amen
    0.76
     mergeFrom
    0.69
    🙏
    0.68
     AMEN
    0.68
     amen
    0.66
     🙏
    0.66
    tagHelperRunner
    0.60
    Activations Density 0.091%

    No Known Activations