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. 7353
    Prev
    Next
    INDEX
    Explanations

    references to legal processes and courtroom discussions

    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
    endforeach
    -0.35
     varones
    -0.32
    UnifiedTopology
    -0.29
    chmod
    -0.29
    sprintf
    -0.28
    @@@@@@@@
    -0.28
     vectorielle
    -0.27
    radan
    -0.27
    營業
    -0.26
     dueños
    -0.26
    POSITIVE LOGITS
    +#+#
    0.95
     صوتيه
    0.65
     MainAxisSize
    0.65
     EconPapers
    0.62
    OrNil
    0.60
    OGND
    0.60
     يتيمه
    0.57
    expandindo
    0.57
    pipes
    0.55
    getMinutes
    0.54
    Activations Density 0.185%

    No Known Activations