© 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 EvalsExportsAPI 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. 11978
    Prev
    Next
    INDEX
    Explanations

    elements related to Japanese sayings and idioms

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

    Incomplete words or fragments

    np_acts-logits-general · gemini-2.0-flash

    incant

    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
     Kraus
    -0.49
     specialist
    -0.43
     Svensson
    -0.42
     Schaefer
    -0.42
     Karlsson
    -0.42
     Forster
    -0.41
     Sloane
    -0.41
     Cohen
    -0.40
    能够
    -0.40
    all
    -0.40
    POSITIVE LOGITS
     surla
    0.76
    httphttps
    0.69
     ModelExpression
    0.65
    RenderAtEndOf
    0.62
    abestanden
    0.60
     виправивши
    0.56
    ésult
    0.56
    存于互联网档案馆
    0.56
     esternos
    0.55
     snippetHide
    0.54
    Activations Density 0.045%

    No Known Activations