© 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. 694
    Prev
    Next
    INDEX
    Explanations

    occurrences of punctuation marks and sentence endings

    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
     accept
    -0.64
     tolerate
    -0.62
     tol
    -0.61
     tolerated
    -0.55
     accepts
    -0.53
     accepter
    -0.51
    toler
    -0.50
     accepting
    -0.49
     Kor
    -0.48
     er
    -0.48
    POSITIVE LOGITS
    ьаж
    0.93
    ThroughAttribute
    0.90
    RegressionTest
    0.83
     houſe
    0.80
     itſelf
    0.80
     raiſ
    0.79
     doubtnut
    0.78
     disambiguazione
    0.78
     greateſt
    0.77
     photolibrary
    0.77
    Activations Density 0.055%

    No Known Activations