© 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. 13277
    Prev
    Next
    INDEX
    Explanations

    specific phrases and numerical data related to statistics or comparisons in various contexts

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

    Numbers followed by units or context

    np_acts-logits-general · gemini-2.0-flash

    risk and numbers

    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
     مشين
    -0.66
     mukana
    -0.59
    RTLR
    -0.59
    majánló
    -0.57
    ########.
    -0.57
    tagHelperRunner
    -0.56
    UnknownFieldSet
    -0.55
     للاسماء
    -0.55
    kloped
    -0.54
     pinulongan
    -0.54
    POSITIVE LOGITS
     significantly
    0.45
     otherwise
    0.40
     regular
    0.40
     Rod
    0.39
     extra
    0.37
    Rod
    0.37
     normal
    0.36
     differently
    0.35
     versus
    0.35
    differ
    0.34
    Activations Density 1.504%

    No Known Activations