© 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. 79692
    Prev
    Next
    INDEX
    Explanations

    references to specific objects or concepts typically indicated by demonstrative pronouns like "this" and "these"

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

    this/these followed by specific item

    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
    GEBURTSDATUM
    -0.63
    thâu
    -0.55
    adays
    -0.52
    colhead
    -0.52
    mpto
    -0.52
    tificate
    -0.52
    masi
    -0.52
    oxyd
    -0.48
    hammad
    -0.47
     betweenstory
    -0.47
    POSITIVE LOGITS
    createStatement
    0.43
     consultato
    0.39
     equal
    0.39
     suplementos
    0.38
     slight
    0.37
     respectivas
    0.37
     kurzen
    0.36
     esprits
    0.36
     final
    0.36
     support
    0.36
    Activations Density 0.089%

    No Known Activations