© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9242
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics or measurements

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

    Numbers as digits

    np_acts-logits-general · gemini-2.0-flash

    6 followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traseiro
    -0.45
     potrzeb
    -0.37
    ้งาน
    -0.37
    addContainerGap
    -0.37
    altezza
    -0.36
     ří
    -0.35
    timbangan
    -0.34
     fondi
    -0.34
     Constitución
    -0.33
    ẹn
    -0.33
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
    +#+
    0.56
     kasarigan
    0.53
    UserScript
    0.52
    ioutil
    0.50
    ptonshire
    0.50
    __":
    0.48
    ConstraintMaker
    0.48
    (!__
    0.48
     allu
    0.47
    Activations Density 0.410%

    No Known Activations