© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10731
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings and administrative processes

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

    preceding reasons or justifications

    np_acts-logits-general · gemini-2.0-flash

    followed by reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.70
    makeConstraints
    -0.68
    Filmografie
    -0.64
    abestanden
    -0.61
     مرئيه
    -0.61
    nloa
    -0.59
    omitempty
    -0.59
    :✨
    -0.56
     oprot
    -0.55
    ConstraintMaker
    -0.55
    POSITIVE LOGITS
     due
    2.92
     because
    2.91
    because
    2.58
     debido
    2.55
    due
    2.52
     devido
    2.37
    Because
    2.31
     karena
    2.29
     BECAUSE
    2.29
     Because
    2.25
    Activations Density 1.679%

    No Known Activations