© 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 EvalsExportsinterp-engineNEWAPI 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. 2928
    Prev
    Next
    INDEX
    Explanations

    elements related to dialogue or conversational context

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

    Japanese text or context

    np_acts-logits-general · gemini-2.0-flash

    analysis results came out

    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
     Dabei
    -0.34
    zczegól
    -0.32
    awm
    -0.32
    kir
    -0.32
    Record
    -0.31
     catena
    -0.31
    kirch
    -0.31
     future
    -0.31
     abad
    -0.30
     daarbij
    -0.30
    POSITIVE LOGITS
    AnimationsModule
    0.55
    いよいよ
    0.55
    tagHelperRunner
    0.55
    DockStyle
    0.54
    protoimpl
    0.52
    !*\
    0.51
     wearing
    0.49
    ArgsConstructor
    0.49
    MarshalTo
    0.48
    plotlib
    0.47
    Activations Density 0.689%

    No Known Activations