© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6170
    Prev
    Next
    INDEX
    Explanations

    headings and section indicators typical of structured written content like reports or articles

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

    official or administrative terminology and references.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    stylers
    -0.74
     Roskov
    -0.70
    oa̍t
    -0.68
     Italijanski
    -0.66
    MessageTagHelper
    -0.66
     otomatig
    -0.66
    posedge
    -0.65
     Chwiliwch
    -0.65
     Italijani
    -0.65
    ⤹
    -0.64
    POSITIVE LOGITS
    OME
    0.40
    lone
    0.36
    pics
    0.35
    olo
    0.35
    选择
    0.35
    ’
    0.35
     udara
    0.34
     arbitrage
    0.34
    rava
    0.34
    oooooooooooooooo
    0.34
    Activations Density 2.752%

    No Known Activations