© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4416
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to computer networks and probabilistic models

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

    Appears before chemical element symbols or codes

    np_acts-logits-general · gemini-2.0-flash

    CC or C words

    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
     inoxydable
    -0.54
    ItemLayout
    -0.53
     Dostupné
    -0.51
     religieuses
    -0.49
     hiér
    -0.48
    expandindo
    -0.48
     sagesse
    -0.48
     /\.(
    -0.48
    StartTag
    -0.48
     endwhile
    -0.47
    POSITIVE LOGITS
     CC
    0.80
    CC
    0.74
    C
    0.73
     C
    0.72
     carbon
    0.70
     centi
    0.69
    𝒞
    0.69
     CWE
    0.67
     Christian
    0.67
     CS
    0.66
    Activations Density 2.315%

    No Known Activations