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. 23-GEMMASCOPE-RES-131K
    6. 23211
    Prev
    Next
    INDEX
    Explanations

    references to wear and deterioration, especially in a home or significant setting

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Metropolitan
    -0.49
     METRO
    -0.47
    الحياه
    -0.47
    Metropolitan
    -0.46
    StoryboardSegue
    -0.46
     Choice
    -0.46
    BeginContext
    -0.45
    osoba
    -0.45
    imie
    -0.45
     QtWidgets
    -0.45
    POSITIVE LOGITS
     kiedyś
    0.44
     scorso
    0.42
     poprzed
    0.40
     afgelopen
    0.39
     HasFactory
    0.39
     precedenti
    0.38
     recent
    0.38
     wcześ
    0.38
     passada
    0.38
     osallist
    0.37
    Activations Density 0.047%

    No Known Activations