© 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. 8238
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals associated with criminal activities or wanted statuses

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

    fugitives, warrants, and bounties

    np_acts-logits-general · gemini-2.0-flash

    fugitive, wanted, arrest warrant, bounty

    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
    ništvo
    -0.64
    posedge
    -0.60
     jsPsych
    -0.55
     VERTICAL
    -0.54
    джет
    -0.53
     propOrder
    -0.53
    ObjectContext
    -0.53
    ashian
    -0.53
    paign
    -0.52
     vertical
    -0.52
    POSITIVE LOGITS
     fugitive
    1.23
     fug
    1.16
     wanted
    1.10
     Wanted
    0.99
    Wanted
    0.97
     hunted
    0.95
    wanted
    0.94
     hunt
    0.88
    fug
    0.88
    Fug
    0.87
    Activations Density 0.326%

    No Known Activations