© 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. 15539
    Prev
    Next
    INDEX
    Explanations

    indicators of significant events or milestones

    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
    ,
    -1.05
    .
    -0.84
    :
    -0.78
     –
    -0.73
     D
    -0.72
     S
    -0.71
    ;
    -0.71
     der
    -0.71
     A
    -0.69
     In
    -0.68
    POSITIVE LOGITS
     Majefty
    1.46
     Efq
    1.42
     itſelf
    1.39
     Houſe
    1.36
     doubtnut
    1.30
     Anſ
    1.25
     Reſ
    1.24
     Jefus
    1.24
     Monfieur
    1.21
     Diſ
    1.19
    Activations Density 0.334%

    No Known Activations