© 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. 12793
    Prev
    Next
    INDEX
    Explanations

    function definitions and related coding syntax

    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
    poptotic
    -0.46
    cheduled
    -0.45
    tabular
    -0.43
     {},
    -0.42
    offsetof
    -0.42
     ambush
    -0.42
    ()]);
    -0.42
    出版年
    -0.41
     interacting
    -0.41
    SuccessListener
    -0.40
    POSITIVE LOGITS
     string
    1.10
     strings
    0.98
     CharSequence
    0.96
     String
    0.90
    string
    0.88
     Strings
    0.86
     characters
    0.85
    Character
    0.85
    CharSequence
    0.85
     str
    0.84
    Activations Density 0.317%

    No Known Activations