© 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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13135
    Prev
    Next
    INDEX
    Explanations

    elements of legal discourse and procedural language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ophysical
    -0.46
    gentle
    -0.45
    كذا
    -0.45
     gentle
    -0.44
     phẩm
    -0.43
    omitempty
    -0.43
     uyar
    -0.42
    тью
    -0.41
     Imb
    -0.40
    delijk
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.73
     cherchés
    0.70
     متعلقه
    0.69
     historique
    0.67
    mergeFrom
    0.67
    IGraphics
    0.66
     historical
    0.65
     الحره
    0.65
    esModule
    0.64
    SerializedSize
    0.63
    Activations Density 1.311%

    No Known Activations