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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1874
    Prev
    Next
    INDEX
    Explanations

    terms related to regulations and compliance in various contexts

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

    Preceding or being a noun, such as "ban on"

    np_acts-logits-general · gemini-2.0-flash

    ads, ban, bid, cap, fit, hit

    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
    uxxxx
    -0.59
    ization
    -0.56
    mente
    -0.53
    ize
    -0.53
    TokenNameLPAREN
    -0.50
    ized
    -0.50
    aires
    -0.49
    ally
    -0.49
    ationen
    -0.49
    Życiorys
    -0.48
    POSITIVE LOGITS
    Билгалдахарш
    0.63
    oredCriteria
    0.50
     Biôgrafia
    0.50
    zeitige
    0.50
    Ӕ
    0.49
     comets
    0.49
    useNewUrlParser
    0.47
    ländische
    0.46
    ArgsConstructor
    0.46
     GoogleFonts
    0.46
    Activations Density 1.993%

    No Known Activations