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. 61607
    Prev
    Next
    INDEX
    Explanations

    key individuals and events related to criminal cases

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

    legal context and dates

    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
    슷
    -0.31
     direto
    -0.30
     historiador
    -0.29
     s
    -0.28
     bø
    -0.28
     equally
    -0.27
     history
    -0.27
     voulu
    -0.27
    empereur
    -0.26
     meaning
    -0.26
    POSITIVE LOGITS
    TagMode
    0.83
    Tembelea
    0.79
    setVerticalGroup
    0.76
     BoxFit
    0.75
    GEBURTSDATUM
    0.74
    GEBURTS
    0.71
     dieſen
    0.71
     zwiſchen
    0.71
     dieſer
    0.71
     ſehr
    0.70
    Activations Density 0.093%

    No Known Activations