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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8952
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations used in equations and formulas

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

    LaTeX math symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical and foreign words

    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
    yntaxException
    -0.79
    DoubleQuotes
    -0.75
    Vidite
    -0.68
     bezeichneter
    -0.64
    postIndex
    -0.63
     المعيارى
    -0.62
    Diweddarwch
    -0.61
     OFDb
    -0.59
    SequentialGroup
    -0.58
    reactstrap
    -0.58
    POSITIVE LOGITS
     uzyska
    0.39
    orologio
    0.38
    insegna
    0.37
     desconocido
    0.34
     Sedangkan
    0.33
     Apabila
    0.33
    depuis
    0.33
    entuh
    0.32
     erscheint
    0.32
    étranger
    0.32
    Activations Density 1.395%

    No Known Activations