© 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
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 14592
    Prev
    Next
    INDEX
    Explanations

    concepts related to explanation and reasoning in scientific contexts

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

    Follows words like explanation, reasons, report, or struggles

    np_acts-logits-general · gemini-2.0-flash

    providing explanations and reasons

    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
    ennifer
    -0.43
     Sha
    -0.34
     sayesinde
    -0.33
    rosh
    -0.32
     Alph
    -0.31
     sæ
    -0.31
    onshire
    -0.30
    penn
    -0.30
     diffuse
    -0.30
    scienced
    -0.30
    POSITIVE LOGITS
    出版年
    0.72
     towards
    0.64
    towards
    0.62
    XtraReports
    0.59
    ValueGeneration
    0.56
     pleaſure
    0.56
     terhadap
    0.56
     toward
    0.56
     fhew
    0.56
    Tikang
    0.54
    Activations Density 0.895%

    No Known Activations