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. 145
    Prev
    Next
    INDEX
    Explanations

    details related to legal procedures and court rulings

    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
     better
    -0.43
     adjust
    -0.35
    better
    -0.34
    riwal
    -0.34
    すみ
    -0.33
    casecmp
    -0.33
    memcmp
    -0.32
    getAbsolutePath
    -0.32
     besser
    -0.32
    ByExample
    -0.32
    POSITIVE LOGITS
    AndEndTag
    0.66
     Probleme
    0.65
     للاسماء
    0.65
     probleem
    0.64
     problems
    0.63
    sproble
    0.63
     problem
    0.62
    problem
    0.61
    problems
    0.61
    crisis
    0.60
    Activations Density 0.043%

    No Known Activations