© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10214
    Prev
    Next
    INDEX
    Explanations

    concepts related to political actions and accountability

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

    Preceding "what" or "What"

    np_acts-logits-general · gemini-2.0-flash

    what after activating words

    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
     SUDOC
    -0.67
    httphttps
    -0.64
    alnız
    -0.63
    parsedMessage
    -0.62
    bool
    -0.57
    WebElementEntity
    -0.56
     defStyleAttr
    -0.55
    Abitanti
    -0.54
     ویکی‌پدیا
    -0.53
     newBuilder
    -0.52
    POSITIVE LOGITS
     what
    4.02
    what
    3.34
    What
    2.78
     What
    2.72
     WHAT
    2.65
    WHAT
    2.49
     whats
    2.12
    whats
    1.98
     hva
    1.91
     hvad
    1.88
    Activations Density 1.057%

    No Known Activations