© 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. 13410
    Prev
    Next
    INDEX
    Explanations

    occurrences of functions and their syntax in code

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

    JavaScript code or code snippets

    np_acts-logits-general · gemini-2.0-flash

    technical terms and foreign languages

    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
    最快更新
    -0.60
     мәкал
    -0.59
    ="@+
    -0.57
    '],$
    -0.56
    ├──
    -0.53
     MQTT
    -0.52
     Eisenberg
    -0.52
    }/${
    -0.52
    libft
    -0.51
     Zink
    -0.51
    POSITIVE LOGITS
     يتيمه
    0.54
     informacija
    0.49
     vandens
    0.46
     idéia
    0.46
     avoient
    0.41
     BoxDecoration
    0.40
     övers
    0.40
     vägen
    0.38
     Könige
    0.38
    didSet
    0.37
    Activations Density 0.056%

    No Known Activations