© 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. 50932
    Prev
    Next
    INDEX
    Explanations

    complex scientific measurements and data representation in various contexts

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

    numbers and symbols

    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
    BagConstraints
    -0.65
    Демографія
    -0.60
    ########.
    -0.57
    ScopeManager
    -0.53
    الحياه
    -0.52
    الإنجليزية
    -0.51
    Erstellt
    -0.50
    Tembelea
    -0.50
     autorytatywna
    -0.49
    屓
    -0.47
    POSITIVE LOGITS
     tampoco
    0.44
     also
    0.39
    endgroup
    0.38
     também
    0.34
     también
    0.34
    ngdoc
    0.33
     тоже
    0.33
     Cruces
    0.32
     consultato
    0.32
     ankaŭ
    0.32
    Activations Density 1.101%

    No Known Activations