© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3085
    Prev
    Next
    INDEX
    Explanations

    technical terms related to encoding processes

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

    Formatting or document structure

    np_acts-logits-general · gemini-2.0-flash

    forest diagrams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    AndEndTag
    -0.94
    RegressionTest
    -0.86
    WriteTagHelper
    -0.75
     snippetHide
    -0.73
    ReusableCell
    -0.70
    RenderAtEndOf
    -0.69
    setVerticalGroup
    -0.68
    !*\
    -0.65
    localctx
    -0.64
    npos
    -0.63
    POSITIVE LOGITS
    enc
    0.54
    ENC
    0.37
    clear
    0.29
     enca
    0.29
     hasard
    0.28
    金
    0.28
     taip
    0.28
    ENCODING
    0.28
     caract
    0.27
    legd
    0.26
    Activations Density 0.000%

    No Known Activations