© 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. 15374
    Prev
    Next
    INDEX
    Explanations

    time periods or intervals associated with specific events or actions

    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
    awaiter
    -0.57
     wireType
    -0.56
    )))));
    -0.54
    zugehen
    -0.53
    WriteLiteral
    -0.53
     BoxFit
    -0.52
     BorderSide
    -0.52
    неопр
    -0.51
    parsedMessage
    -0.50
    Filmographie
    -0.50
    POSITIVE LOGITS
    enumi
    0.82
     arrival
    0.74
     enactment
    0.72
     publication
    0.71
     receipt
    0.70
     onset
    0.68
     issuance
    0.66
     commencement
    0.63
     inception
    0.62
    parseFrom
    0.61
    Activations Density 0.480%

    No Known Activations