© 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. 11-GEMMASCOPE-RES-16K
    11. 1722
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of a document or section, indicated by the use of specific markers or tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.75
    TagMode
    -0.72
    LayoutStyle
    -0.61
    Pautan
    -0.58
     gynhyrchwyd
    -0.56
     Etr
    -0.56
    Voir
    -0.54
    mmä
    -0.53
    alegal
    -0.53
    $_['
    -0.53
    POSITIVE LOGITS
     jLabel
    0.51
    StoryboardSegue
    0.50
    protoc
    0.49
     समीक्षाओं
    0.48
    Aholisi
    0.48
    Bibliograf
    0.48
    UnsafeEnabled
    0.47
    iola
    0.47
     diſt
    0.46
    WebVitals
    0.43
    Activations Density 0.204%

    No Known Activations