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. 114548
    Prev
    Next
    INDEX
    Explanations

    expressions and words indicating value perception and cost

    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
    findpost
    -0.46
    queryInterface
    -0.40
     IFTT
    -0.40
     propOrder
    -0.40
     Auff
    -0.40
    gameserver
    -0.39
     continúas
    -0.38
    schirm
    -0.38
    spitze
    -0.38
    
    -0.38
    POSITIVE LOGITS
    chränk
    0.49
    Matchers
    0.45
     "','
    0.45
    denly
    0.44
     /\.(
    0.43
     sexy
    0.43
    addPreferredGap
    0.43
    ovatel
    0.42
     savoury
    0.42
    HttpMethod
    0.41
    Activations Density 0.028%

    No Known Activations