© 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. 19-GEMMASCOPE-RES-16K
    11. 1676
    Prev
    Next
    INDEX
    Explanations

    punctuation and its context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.67
     Chwiliwch
    -0.59
    RenderAtEndOf
    -0.58
     people
    -0.56
     modern
    -0.56
    躇
    -0.53
     window
    -0.51
    헌
    -0.51
    ège
    -0.51
    Clr
    -0.50
    POSITIVE LOGITS
    Despite
    0.67
     Damit
    0.66
     Despite
    0.64
     avenge
    0.63
    resave
    0.63
    Rookie
    0.62
     disponibilités
    0.62
     Pourtant
    0.61
    Reign
    0.61
    Trailing
    0.60
    Activations Density 0.148%

    No Known Activations