© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22006
    Prev
    Next
    INDEX
    Explanations

    references to errors or warnings in technical contexts

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

    error, compounds, meaning, falls

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     min
    -0.40
     ver
    -0.38
    wer
    -0.37
    nov
    -0.36
    Diweddarwch
    -0.36
     نشست
    -0.34
    VertexArray
    -0.34
     boven
    -0.34
     mon
    -0.33
     ber
    -0.33
    POSITIVE LOGITS
    oredCriteria
    0.71
     surla
    0.64
    帖最后由
    0.60
     kasarigan
    0.49
    tagHelperRunner
    0.48
     pleaſure
    0.48
    JspWriter
    0.47
    Personensuche
    0.46
    ViewInit
    0.46
    ſelf
    0.45
    Activations Density 0.215%

    No Known Activations