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. 117357
    Prev
    Next
    INDEX
    Explanations

    phrases related to judicial discretion and decision-making in court cases

    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
    OGND
    -0.71
    ########.
    -0.66
    prefixer
    -0.64
    ChildScrollView
    -0.62
    DockStyle
    -0.62
    httphttps
    -0.62
     للاسماء
    -0.61
     kasarigan
    -0.61
    WebElementEntity
    -0.61
     مشين
    -0.59
    POSITIVE LOGITS
     decision
    0.46
     decide
    0.42
     whether
    0.38
     decisions
    0.36
     decides
    0.35
     deciding
    0.34
    decision
    0.34
     decided
    0.32
     décisions
    0.31
    决定
    0.30
    Activations Density 0.049%

    No Known Activations