© 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. 31-GEMMASCOPE-RES-16K
    6. 4687
    Prev
    Next
    INDEX
    Explanations

    occurrences of proper nouns and identifiers related to titles or names

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

    numbers and numerical sequences, particularly years and date formats.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kebijakan
    -0.59
     étoit
    -0.56
     étranger
    -0.54
     Penga
    -0.53
     Bidang
    -0.52
     Komunikasi
    -0.52
     Keuangan
    -0.50
     Umum
    -0.49
     mourut
    -0.47
     Manfaat
    -0.47
    POSITIVE LOGITS
     laſſen
    0.79
    enablog
    0.73
    otropy
    0.71
     tartalo
    0.71
     ſeinen
    0.70
     Geiſt
    0.70
    ᅝ
    0.69
     メンテナ
    0.69
    <unused76>
    0.69
    <unused43>
    0.69
    Activations Density 0.014%

    No Known Activations