© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal relationships and agency in context

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

    Prepositions followed by "behalf" or "basis"

    np_acts-logits-general · gemini-2.0-flash

    on his behalf

    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
     EconPapers
    -0.80
    providedIn
    -0.68
     Chwiliwch
    -0.64
    ModelSerializer
    -0.63
    enumii
    -0.63
    addCriterion
    -0.62
    ⓧ
    -0.61
    )});
    -0.59
    "]));
    -0.57
    */;
    -0.57
    POSITIVE LOGITS
     behalf
    1.56
     basis
    1.22
     occasion
    1.17
     occasions
    1.16
     ועל
    1.06
    basis
    0.92
     grounds
    0.88
     fronts
    0.85
     occas
    0.80
     occa
    0.77
    Activations Density 0.482%

    No Known Activations