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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122813
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks and their frequencies in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    évaluateur
    -0.79
    :✨
    -0.66
    MLLoader
    -0.65
    CloseOperation
    -0.63
    GIVEREF
    -0.62
    WriteTagHelper
    -0.61
    AndEndTag
    -0.59
     Monfieur
    -0.57
     للاسماء
    -0.56
    AxisAlignment
    -0.54
    POSITIVE LOGITS
    (:,:,
    0.49
    3
    0.46
     III
    0.44
     Third
    0.42
     Str
    0.41
    pausal
    0.40
     Rank
    0.39
     THIRD
    0.39
     Three
    0.39
     rank
    0.39
    Activations Density 0.065%

    No Known Activations