Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 61773
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude or congratulations

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

    headings, quotes, and thanks

    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
     miniaturka
    -0.49
    inheritDoc
    -0.41
    település
    -0.40
     contextLoads
    -0.40
     månader
    -0.40
    ENDIAN
    -0.39
    HasColumnName
    -0.39
    يكب
    -0.39
     endblock
    -0.39
    MIDDLEWARE
    -0.38
    POSITIVE LOGITS
    tags
    0.41
    Sprintf
    0.40
    soort
    0.38
    Lup
    0.37
     kdy
    0.36
     Stil
    0.36
     Privacidad
    0.36
     flavor
    0.35
     examples
    0.35
    readlines
    0.35
    Activations Density 0.038%

    No Known Activations