© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2709
    Prev
    Next
    INDEX
    Explanations

    metrics related to diseases and their evaluations

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

    Values followed by "greater than" or "above."

    np_acts-logits-general · gemini-2.0-flash

    values greater than a threshold

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.53
     సౌకర్య
    -0.47
    protoimpl
    -0.45
     ***!
    -0.38
    argento
    -0.37
     peł
    -0.36
    InitVars
    -0.36
     समीक्षाओं
    -0.36
    sendStatus
    -0.36
    Leftrightarrow
    -0.36
    POSITIVE LOGITS
     exceeds
    1.54
     exceed
    1.49
     exceeding
    1.45
     greater
    1.44
     exceeded
    1.29
    greater
    1.27
     surpass
    1.25
     surpasses
    1.20
     surpassing
    1.14
    大于
    1.13
    Activations Density 1.012%

    No Known Activations