© 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. 22-GEMMASCOPE-RES-16K
    11. 15149
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations and legal proceedings

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

    preceding a name or entity

    np_acts-logits-general · gemini-2.0-flash

    police, jury, investigator, Commission, Republicans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     by
    -1.63
    by
    -1.27
     By
    -1.20
    By
    -1.19
     oleh
    -0.99
     BY
    -0.98
     توسط
    -0.93
    bys
    -0.91
     getBy
    -0.86
    BY
    -0.78
    POSITIVE LOGITS
     soins
    0.84
     hindurch
    0.78
     setempat
    0.72
    RenderAtEndOf
    0.65
     selaku
    0.63
     correctes
    0.62
     autorité
    0.61
    UrlResolution
    0.60
     who
    0.59
     using
    0.59
    Activations Density 0.499%

    No Known Activations