© 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. 5-GEMMASCOPE-RES-16K
    11. 13808
    Prev
    Next
    INDEX
    Explanations

    references to user interface elements, particularly cards and modals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scre
    -0.59
    ranslated
    -0.55
     quantit
    -0.53
    Étymologie
    -0.53
     californ
    -0.52
     handker
    -0.51
     inflo
    -0.50
    XMLSchema
    -0.49
    SIGINT
    -0.49
     Dances
    -0.48
    POSITIVE LOGITS
    card
    1.02
    Card
    0.83
     card
    0.82
    tagHelperRunner
    0.78
     BoxDecoration
    0.75
    </thead>
    0.73
     Card
    0.72
    CardHeader
    0.65
     autorytatywna
    0.64
    ValueStyle
    0.61
    Activations Density 0.049%

    No Known Activations