© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8083
    Prev
    Next
    INDEX
    Explanations

    terms related to the 'Orange' context in various applications or mentions

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

    Appears before capitalized words or identifiers

    np_acts-logits-general · gemini-2.0-flash

    Marshall, pump, SB, Vander

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ">—
    -0.63
    UMBIA
    -0.60
    Abp
    -0.59
    +#+#
    -0.56
    Jeografia
    -0.56
     Wallflower
    -0.56
    ={`/
    -0.54
     Loos
    -0.54
     levure
    -0.54
     defaultstate
    -0.53
    POSITIVE LOGITS
    enumii
    0.86
    Gambas
    0.79
    IBOutlet
    0.74
    ization
    0.73
    FieldBuilder
    0.70
    ]--;
    0.69
     ―――――
    0.68
     BorderRadius
    0.66
    iress
    0.65
    GraphicsUnit
    0.64
    Activations Density 0.626%

    No Known Activations