© 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. 15807
    Prev
    Next
    INDEX
    Explanations

    references to lists, collections, and items within a context of organization or management

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

    Followed by Japanese/Chinese particles

    np_acts-logits-general · gemini-2.0-flash

    where

    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
    \{\\
    -0.66
    RenderAtEndOf
    -0.63
    atero
    -0.59
    
    -0.57
    enumii
    -0.55
    ########.
    -0.54
    fficients
    -0.53
    OWSKI
    -0.52
     Houſe
    -0.51
    enumi
    -0.51
    POSITIVE LOGITS
     where
    1.16
    where
    0.95
    에서
    0.91
     où
    0.90
     donde
    0.83
    에
    0.81
    Where
    0.80
     Where
    0.78
     में
    0.77
    donde
    0.74
    Activations Density 0.046%

    No Known Activations