© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1679
    Prev
    Next
    INDEX
    Explanations

    mentions of reference materials or citations

    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
    ArgsConstructor
    -0.68
    enumii
    -0.59
    Còn
    -0.58
    EndContext
    -0.53
     recessive
    -0.51
    GraphicsUnit
    -0.50
    nsics
    -0.49
    istics
    -0.49
    ografija
    -0.48
    doPost
    -0.48
    POSITIVE LOGITS
    Refer
    0.91
     Refs
    0.89
     refs
    0.89
     references
    0.88
     refer
    0.87
     REF
    0.87
     References
    0.83
     Refer
    0.83
    REF
    0.78
     allude
    0.77
    Activations Density 0.296%

    No Known Activations