© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7219
    Prev
    Next
    INDEX
    Explanations

    questions that start with "What" and require specific information or definitions

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

    Questions starting with "What" followed by "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    "What is/are/am" questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.56
     endregion
    -0.54
     [*]
    -0.52
    __('
    -0.49
    })*/
    -0.49
    seins
    -0.47
    endfor
    -0.47
    posedge
    -0.47
    -------
    -0.46
    <_>
    -0.46
    POSITIVE LOGITS
    What
    0.52
    —¿
    0.48
    Isn
    0.48
    怎麼辦
    0.46
     habla
    0.45
    ?
    0.45
     What
    0.45
     Wikiseite
    0.45
     anderer
    0.45
     árabe
    0.45
    Activations Density 0.153%

    No Known Activations