© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10354
    Prev
    Next
    INDEX
    Explanations

    phrases related to intervention and involvement in geopolitical dynamics

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

    intervention or objection

    np_acts-logits-general · gemini-2.0-flash

    intervene or step in like counsel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nationality
    -0.60
    TintMode
    -0.56
    ografija
    -0.55
    ErrUnexpectedEOF
    -0.55
    expandindo
    -0.54
     Мексичка
    -0.53
     Paglinawan
    -0.53
     onBind
    -0.52
    SourceChecksum
    -0.52
    astéro
    -0.52
    POSITIVE LOGITS
     intervene
    1.56
     intervened
    1.56
     stepped
    1.53
     stepping
    1.38
     interven
    1.34
     step
    1.34
     intervening
    1.30
     steps
    1.25
     intervenir
    1.22
    step
    1.21
    Activations Density 0.305%

    No Known Activations