© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2919
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "open up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.68
    المكان
    -0.53
    DropColumn
    -0.49
    ChildIndex
    -0.48
    InjectAttribute
    -0.47
     NDL
    -0.47
    noid
    -0.47
    baric
    -0.46
     gạch
    -0.46
    psack
    -0.45
    POSITIVE LOGITS
     EconPapers
    0.71
     مشين
    0.70
    ("")]
    0.66
    NUMX
    0.63
    %";
    0.62
     BoxDecoration
    0.62
    parsedMessage
    0.61
     المعيارى
    0.60
    "]="
    0.60
    NewUrlParser
    0.59
    Activations Density 0.382%

    No Known Activations