© 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. 24-GEMMASCOPE-RES-16K
    6. 259
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and judicial figures

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

    Appearing before an authority figure

    np_acts-logits-general · gemini-2.0-flash

    legal proceedings and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.69
     للاسماء
    -0.68
    oa̍t
    -0.64
     desmotivaciones
    -0.63
    Personensuche
    -0.62
     CreateTagHelper
    -0.61
    majánló
    -0.61
     surla
    -0.61
    resizingMask
    -0.60
     snippetHide
    -0.60
    POSITIVE LOGITS
     further
    0.42
     says
    0.36
    ta
    0.34
    HtmlAttribute
    0.34
     also
    0.34
     dub
    0.33
     noted
    0.33
     calls
    0.33
     judge
    0.33
     pres
    0.32
    Activations Density 0.504%

    No Known Activations