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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10508
    Prev
    Next
    INDEX
    Explanations

    entities and references related to specific locations, individuals, and scientific terms

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

    geographic or location names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     Erlangen
    -0.33
    hadap
    -0.33
    ufig
    -0.32
     pos
    -0.31
    iego
    -0.30
    piro
    -0.28
    proj
    -0.28
     activity
    -0.28
     REFR
    -0.28
     silver
    -0.27
    POSITIVE LOGITS
    BufferException
    0.71
    webElementGuid
    0.70
     المعيارى
    0.69
     kasarigan
    0.68
    enderror
    0.68
    EDEFAULT
    0.68
    HtmlAttribute
    0.67
    Aktualisiert
    0.66
    Diweddarwch
    0.65
    featureID
    0.63
    Activations Density 0.693%

    No Known Activations