© 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. 20-GEMMASCOPE-RES-16K
    11. 15267
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to judicial proceedings and constitutional rights

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

    a negative condition or insufficient action

    np_acts-logits-general · gemini-2.0-flash

    not constituting or qualifying

    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
    Personensuche
    -0.68
     ModelExpression
    -0.61
    >`;
    -0.57
     []).
    -0.54
     CGPoint
    -0.53
    спери
    -0.50
    ']));
    -0.50
    Autoritní
    -0.49
     emphasis
    -0.49
    [])
    -0.49
    POSITIVE LOGITS
     qualify
    1.36
     qualifies
    1.36
     constitutes
    1.12
     constitute
    1.10
     counts
    1.04
     qualified
    0.97
     qualifying
    0.96
     counted
    0.95
     count
    0.94
    qual
    0.90
    Activations Density 1.290%

    No Known Activations