Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 52558
    Prev
    Next
    INDEX
    Explanations

    terms related to legal definitions and frameworks surrounding emotional distress claims in the workplace

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     мәкал
    -0.35
     conj
    -0.33
    ​
    -0.31
    3
    -0.31
     l
    -0.31
    CT
    -0.31
    CH
    -0.31
     Cand
    -0.30
     P
    -0.30
    Q
    -0.30
    POSITIVE LOGITS
    parsedMessage
    0.78
    fromnode
    0.77
     Audiodateien
    0.74
     onCreateView
    0.73
    principalColumn
    0.72
     виправивши
    0.72
    oa̍t
    0.71
     تضيفلها
    0.68
    verwijspagina
    0.67
    expandindo
    0.66
    Activations Density 0.155%

    No Known Activations