© 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. 15241
    Prev
    Next
    INDEX
    Explanations

    references to tabulations or data organization

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

    "Tab" or "Table" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    tab pages and tables

    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
     runt
    -0.54
    ]--;
    -0.47
     grand
    -0.46
    ródła
    -0.45
     Dead
    -0.45
     Bea
    -0.45
    ServiceException
    -0.45
     furt
    -0.44
    ]>=
    -0.44
     Bore
    -0.43
    POSITIVE LOGITS
    StructEnd
    0.99
    WebVitals
    0.82
     تانيه
    0.81
     tab
    0.81
     Tab
    0.80
     myſelf
    0.78
     TAB
    0.77
    Tab
    0.77
     createState
    0.73
     Tabs
    0.73
    Activations Density 0.071%

    No Known Activations