© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11663
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and qualifications in statements

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

    after dashes or symbols

    np_acts-logits-general · gemini-2.0-flash

    financial or legal contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.32
     Sedangkan
    -0.32
     itp
    -0.32
     etc
    -0.32
     I
    -0.31
     itd
    -0.30
    wesenheit
    -0.30
     stating
    -0.29
    感じで
    -0.28
     sedangkan
    -0.28
    POSITIVE LOGITS
    parsedMessage
    0.80
     disambiguazione
    0.76
    uxxxx
    0.75
    !—
    0.66
    مصادر
    0.66
     initComponents
    0.65
    –
    0.64
    ​—
    0.62
     ujednoznacz
    0.59
    -};
    0.58
    Activations Density 0.340%

    No Known Activations