© 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. 13-GEMMASCOPE-RES-16K
    11. 4566
    Prev
    Next
    INDEX
    Explanations

    specific nouns and actions related to characters and their interactions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raisonnable
    -0.68
     pouvoit
    -0.66
     comprends
    -0.60
    ktop
    -0.60
    lanze
    -0.60
     préfé
    -0.60
    adeloupe
    -0.59
    GOTREF
    -0.59
     auroit
    -0.58
    delige
    -0.58
    POSITIVE LOGITS
    query
    0.52
     whose
    0.49
     another
    0.48
     recently
    0.46
     RSSSF
    0.45
     Lordships
    0.45
    RenderAtEndOf
    0.45
    tito
    0.44
     recientemente
    0.44
     claimed
    0.43
    Activations Density 0.552%

    No Known Activations