© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13379
    Prev
    Next
    INDEX
    Explanations

    references or citations within academic or technical documents

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

    References, citations, or tables

    np_acts-logits-general · gemini-2.0-flash

    apache type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    Jeografia
    -0.68
    InitVars
    -0.54
     <>",
    -0.53
    WebElementEntity
    -0.52
    TagMode
    -0.50
     beweisen
    -0.48
     Chwiliwch
    -0.47
    ConstraintMaker
    -0.47
     pungkasnya
    -0.45
     esternos
    -0.44
    POSITIVE LOGITS
     tille
    0.45
     Melon
    0.45
     Fall
    0.43
     Spotify
    0.43
     Cymru
    0.43
     Client
    0.42
    Typed
    0.41
    ByType
    0.41
     Sponsor
    0.41
     Fuse
    0.41
    Activations Density 1.597%

    No Known Activations