© 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. 15881
    Prev
    Next
    INDEX
    Explanations

    references to proper nouns and names

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

    ending in "id" or "da"

    np_acts-logits-general · gemini-2.0-flash

    Bid, Vid, Sid, Rid IDs

    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
    er
    -0.65
    ه
    -0.60
    }());
    -0.60
    erty
    -0.59
    \}\\
    -0.57
    mbggenerated
    -0.54
    es
    -0.53
    erah
    -0.52
    — 
    -0.52
    s
    -0.52
    POSITIVE LOGITS
    RenderAtEndOf
    0.79
     unknownFields
    0.75
    +#+#
    0.73
    genossen
    0.72
    tagHelperRunner
    0.72
     BID
    0.71
    #+#
    0.71
    irectional
    0.67
    bids
    0.66
     Bid
    0.66
    Activations Density 0.126%

    No Known Activations