© 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. 9-GEMMASCOPE-RES-16K
    11. 341
    Prev
    Next
    INDEX
    Explanations

    type-checking statements and functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    -0.71
     złota
    -0.67
     místa
    -0.66
     nakalista
    -0.64
     cavallo
    -0.63
     piedi
    -0.62
     państw
    -0.62
    ます
    -0.61
     munc
    -0.61
     szükség
    -0.61
    POSITIVE LOGITS
    typeof
    1.79
     typeof
    1.60
    Personendaten
    0.86
    posób
    0.79
    קישורים
    0.78
     оригіналу
    0.78
    reshold
    0.78
    Lähteet
    0.75
    Kanpo
    0.74
    ntype
    0.73
    Activations Density 0.036%

    No Known Activations