© 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. 13620
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and actions

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

    Follows questions

    np_acts-logits-general · gemini-2.0-flash

    we as subjects

    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
    ेशा
    -0.72
    THISDAY
    -0.63
     Administrativna
    -0.62
    oredCriteria
    -0.61
    ')['
    -0.60
    setVerticalGroup
    -0.60
    ))[
    -0.57
    انجليز
    -0.57
     ')[
    -0.56
    VersionUID
    -0.55
    POSITIVE LOGITS
     we
    3.59
     our
    3.29
     ourselves
    2.85
    我們
    2.68
    我们
    2.63
    We
    2.61
     We
    2.55
    我們的
    2.38
    我们的
    2.34
    Our
    2.32
    Activations Density 3.991%

    No Known Activations