© 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. 5494
    Prev
    Next
    INDEX
    Explanations

    references to economic studies and assessments

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

    Appearing before or related to legal bodies

    np_acts-logits-general · gemini-2.0-flash

    official reports and statements

    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
     Whilst
    -1.52
    Whilst
    -1.46
     whilst
    -1.21
     enquiry
    -1.00
     Amongst
    -0.95
     Schluß
    -0.93
     läßt
    -0.90
     poichè
    -0.88
     Honourable
    -0.87
    luß
    -0.85
    POSITIVE LOGITS
     
    0.97
     —
    0.96
     ¦
    0.93
    ¦
    0.89
     --
    0.84
     ``
    0.83
     
    0.83
    ,’’
    0.80
    
    0.80
    ,''
    0.78
    Activations Density 1.309%

    No Known Activations