© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8847
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    arXiv or DOIs

    np_acts-logits-general · gemini-2.0-flash

    publication identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rxjs
    -0.59
     typelib
    -0.59
    Portale
    -0.57
    Parcelize
    -0.57
     InputDecoration
    -0.54
     تضيفلها
    -0.53
    ScopeManager
    -0.53
    ValueStyle
    -0.53
     Walkover
    -0.51
    styrelsen
    -0.51
    POSITIVE LOGITS
    قایناق‌لار
    0.59
    tersebut
    0.54
     Italij
    0.52
     ſeveral
    0.51
    bibinfo
    0.51
    ThroughAttribute
    0.50
     doubtnut
    0.50
    onOptions
    0.50
     myſelf
    0.49
     تكبرها
    0.49
    Activations Density 0.890%

    No Known Activations