© 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. 2970
    Prev
    Next
    INDEX
    Explanations

    terms related to introspection and self-regulation

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

    [verb] down

    np_acts-logits-general · gemini-2.0-flash

    narrow down, calm down, slow down

    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
    Hochspringen
    -0.58
    utico
    -0.56
    usermodel
    -0.53
    arcas
    -0.53
    cyjnych
    -0.52
     ModelExpression
    -0.52
    ]='\
    -0.49
     lí
    -0.48
    hibian
    -0.48
     BorderRadius
    -0.46
    POSITIVE LOGITS
     down
    4.28
    down
    3.56
    Down
    3.42
     Down
    3.33
     DOWN
    3.15
    DOWN
    2.93
    downs
    2.55
     downs
    2.31
    ダウン
    2.30
     dow
    1.94
    Activations Density 0.412%

    No Known Activations