© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14746
    Prev
    Next
    INDEX
    Explanations

    programming constructs and elements related to file handling and definitions in code

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

    C code or file paths

    np_acts-logits-general · gemini-2.0-flash

    shell commands and variable expansion

    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
     للمعارف
    -0.79
     EconPapers
    -0.75
     חיצוניים
    -0.73
    httphttps
    -0.73
     autorytatywna
    -0.70
    endphp
    -0.69
    adaptiveStyles
    -0.69
    锈钢
    -0.68
     CreateTagHelper
    -0.66
    Portail
    -0.65
    POSITIVE LOGITS
     Königreich
    0.33
    Ак
    0.32
    super
    0.32
     Royaume
    0.30
     upor
    0.29
    che
    0.29
    TextSpan
    0.28
    ak
    0.28
     Sitzung
    0.28
    set
    0.28
    Activations Density 0.843%

    No Known Activations