© 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. 8618
    Prev
    Next
    INDEX
    Explanations

    terms related to legal procedures and conditions of political candidates

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

    Following a subject, predicts "may" or "should"

    np_acts-logits-general · gemini-2.0-flash

    subjects followed by may or shall

    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
    providedIn
    -0.68
     समीक्षाओं
    -0.62
    Personendaten
    -0.60
     estimés
    -0.56
    expandindo
    -0.56
    رشف
    -0.54
    TypedDataSet
    -0.54
    ratis
    -0.52
    InlineData
    -0.49
    amazonaws
    -0.49
    POSITIVE LOGITS
     may
    2.62
    may
    2.36
     May
    2.14
    May
    2.13
     MAY
    2.02
    MAY
    1.83
     shall
    1.51
    shall
    1.32
     must
    1.22
     może
    1.19
    Activations Density 0.485%

    No Known Activations