© 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. 16-GEMMASCOPE-RES-16K
    6. 5333
    Prev
    Next
    INDEX
    Explanations

    relationships between various factors that affect performance and outcomes in scientific studies

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

    Something that "controls" or "affects" something else

    np_acts-logits-general · gemini-2.0-flash

    governs frequency or rate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.74
     estekak
    -0.71
     initComponents
    -0.69
     дописавши
    -0.67
     للمعارف
    -0.67
    Hochspringen
    -0.60
    ChildScrollView
    -0.60
    WithIOException
    -0.57
    GOTREF
    -0.57
    <bos>
    -0.56
    POSITIVE LOGITS
     affects
    0.74
     determines
    0.74
    affect
    0.72
     influencing
    0.71
     influences
    0.71
     Einfluss
    0.71
     affect
    0.71
     determining
    0.70
    Decisions
    0.70
     Influences
    0.70
    Activations Density 0.977%

    No Known Activations