© 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. 13946
    Prev
    Next
    INDEX
    Explanations

    mentions of specific pharmaceutical terms and biological markers

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

    starting with "x" and followed by other letters

    np_acts-logits-general · gemini-2.0-flash

    Dextr, Raxone, Trixie, Saxena

    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
    SharedDtor
    -0.45
    featureID
    -0.41
    있
    -0.39
    VELAND
    -0.39
    ScopeManager
    -0.38
    ensburg
    -0.38
    angering
    -0.38
    ている
    -0.38
    tl
    -0.37
     autorytatywna
    -0.37
    POSITIVE LOGITS
    NUMX
    0.71
    xon
    0.62
    xis
    0.62
    x
    0.60
    xam
    0.56
    qx
    0.56
    xes
    0.55
     Mex
    0.55
    mox
    0.55
    rx
    0.54
    Activations Density 1.237%

    No Known Activations