© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8869
    Prev
    Next
    INDEX
    Explanations

    signals and thresholds in data processing contexts

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

    after specific identifiers or keywords

    np_acts-logits-general · gemini-2.0-flash

    identifier or award following common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kjelder
    -0.45
     ब्रेकडाउन
    -0.42
    __(/*!
    -0.38
    verifyException
    -0.38
    WritableDatabase
    -0.38
    исленность
    -0.37
    MigrationBuilder
    -0.37
    TableField
    -0.37
    scriptcase
    -0.36
    Gameplay
    -0.34
    POSITIVE LOGITS
    RectangleBorder
    0.59
    withId
    0.59
     seigneur
    0.50
    withIdentifier
    0.49
     EconPapers
    0.48
    prefixer
    0.47
    ajinan
    0.46
     voucher
    0.46
    formik
    0.45
     zitate
    0.45
    Activations Density 2.695%

    No Known Activations