© 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. 1723
    Prev
    Next
    INDEX
    Explanations

    references to resources, recommendations, or guides for further information and study

    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
    WebElementEntity
    -0.79
    elemField
    -0.59
    expandindo
    -0.56
    ,:);
    -0.55
    webElementXpaths
    -0.54
    Distribuzione
    -0.52
     Biôgrafia
    -0.49
    yfikacja
    -0.49
    RTEE
    -0.48
    Попис
    -0.48
    POSITIVE LOGITS
     reference
    1.66
     refer
    1.51
    reference
    1.36
     references
    1.30
     Refer
    1.28
     REFERENCE
    1.28
     Reference
    1.28
    refer
    1.25
     referencing
    1.25
     REFER
    1.24
    Activations Density 0.569%

    No Known Activations