© 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. 14809
    Prev
    Next
    INDEX
    Explanations

    variations of the word "go" used in different contexts

    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
     myst
    -0.76
    ként
    -0.76
     Teich
    -0.73
     ję
    -0.73
    minyak
    -0.73
     Terrasse
    -0.72
     purpoſe
    -0.72
     itſelf
    -0.70
    fficiency
    -0.69
     Majefty
    -0.68
    POSITIVE LOGITS
     go
    1.65
     goes
    1.44
    Goes
    1.39
    Go
    1.35
     Goes
    1.35
     going
    1.34
     Go
    1.32
    go
    1.29
     went
    1.27
     GO
    1.26
    Activations Density 0.121%

    No Known Activations