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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8197
    Prev
    Next
    INDEX
    Explanations

    references to incidents and events, particularly those involving crimes, investigations, or accidents

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

    "incident" or similar events

    np_acts-logits-general · gemini-2.0-flash

    events and incidents

    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
    eloma
    -0.51
    Demografía
    -0.50
     sẵn
    -0.49
    lless
    -0.47
    ليد
    -0.47
    frow
    -0.46
    oprene
    -0.46
    ROG
    -0.45
    Externí
    -0.45
    calipsis
    -0.45
    POSITIVE LOGITS
     involving
    1.49
     occurred
    1.48
     occurring
    1.35
     ocor
    1.24
     Occur
    1.20
     happened
    1.19
     occured
    1.19
    occur
    1.18
     occur
    1.17
     ocurrido
    1.12
    Activations Density 0.465%

    No Known Activations