© 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. 3358
    Prev
    Next
    INDEX
    Explanations

    URLs and associated links in text

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

    URLs and code snippets

    np_acts-logits-general · gemini-2.0-flash

    pic, twitter, tweeted

    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
     disambiguazione
    -0.66
    Bibliograf
    -0.66
    mybatisplus
    -0.64
    Autoritní
    -0.58
     capito
    -0.58
    
    -0.55
    ✨:
    -0.54
     mathématiques
    -0.52
     siyang
    -0.52
    DataAnnotations
    -0.52
    POSITIVE LOGITS
     pic
    0.92
    —
    0.89
    pic
    0.75
     twitter
    0.71
     —
    0.68
    .—
    0.67
    ?—
    0.66
    €”
    0.61
    )—
    0.60
     tweeted
    0.60
    Activations Density 0.050%

    No Known Activations