© 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 EvalsExportsAPI 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. 6656
    Prev
    Next
    INDEX
    Explanations

    references to legislation and legal matters

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

    Tokens preceding numbers

    np_acts-logits-general · gemini-2.0-flash

    Green Party terrorism

    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
    ByExample
    -0.29
     mécan
    -0.28
     Ministério
    -0.28
    Probl
    -0.27
    knex
    -0.27
     muebles
    -0.27
     lâm
    -0.26
     verkoop
    -0.26
     arreglar
    -0.26
    rašymas
    -0.26
    POSITIVE LOGITS
     terrorist
    1.25
     terrorists
    1.18
    terror
    1.13
     terrorism
    1.09
    Terror
    1.00
     Terror
    0.98
     Terrorism
    0.97
     terror
    0.96
    terrorism
    0.90
     terrorismo
    0.85
    Activations Density 0.179%

    No Known Activations