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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12405
    Prev
    Next
    INDEX
    Explanations

    references to European institutions, entities, or initiatives

    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
    GetKeyDown
    -0.63
    IVEREF
    -0.56
     WaitForSeconds
    -0.56
    новниш
    -0.52
    Демографія
    -0.50
    InSection
    -0.49
    ConstraintMaker
    -0.49
    GARY
    -0.48
     beginnetje
    -0.48
    SourceChecksum
    -0.48
    POSITIVE LOGITS
     Union
    1.17
    Union
    1.06
     UNION
    0.97
     union
    0.81
    UNION
    0.78
     EURO
    0.77
     Unión
    0.76
     Unions
    0.74
     continent
    0.74
     euros
    0.72
    Activations Density 0.063%

    No Known Activations