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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 92818
    Prev
    Next
    INDEX
    Explanations

    references to male and female subjects in the text

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

    pronoun and additional action

    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
    
    -0.80
    Personendaten
    -0.68
    IntoConstraints
    -0.65
    richTextPanel
    -0.65
    uxxxx
    -0.65
     ffilmiau
    -0.64
    awtextra
    -0.62
    Rüyada
    -0.61
    >//
    -0.59
    ChildScrollView
    -0.58
    POSITIVE LOGITS
     ayrıca
    0.63
     also
    0.63
     dezelve
    0.61
     dessutom
    0.57
     tevens
    0.57
     также
    0.56
     zelve
    0.55
     także
    0.54
     dalamnya
    0.53
     також
    0.52
    Activations Density 0.011%

    No Known Activations