© 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. 3273
    Prev
    Next
    INDEX
    Explanations

    elements related to data analysis and graphical representation

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

    after certain punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    higher values or specific metrics

    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
    TagMode
    -0.56
    __).
    -0.55
    seam
    -0.52
    majánló
    -0.52
    VYMaps
    -0.51
     Quota
    -0.50
    __":
    -0.50
    IndentedString
    -0.49
     الحره
    -0.49
    msgTypes
    -0.49
    POSITIVE LOGITS
    nalités
    0.36
    LabelTagHelper
    0.32
    ביוגרפיה
    0.31
    archiviato
    0.31
    ########.
    0.31
    ősz
    0.31
    ward
    0.30
     different
    0.28
    laufen
    0.28
    NullException
    0.28
    Activations Density 1.585%

    No Known Activations