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. 8063
    Prev
    Next
    INDEX
    Explanations

    mentions of familial relationships, particularly regarding mothers and fathers

    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
    principalColumn
    -0.51
     arbitrage
    -0.48
    tawan
    -0.47
     calendriers
    -0.47
     houſe
    -0.47
    istics
    -0.47
    щадь
    -0.47
    Insee
    -0.46
    enido
    -0.46
    ereum
    -0.46
    POSITIVE LOGITS
    queryInterface
    0.47
     GenerationType
    0.46
    DockStyle
    0.38
     NSCoder
    0.36
    ArrowToggle
    0.36
    contentLoaded
    0.35
    TargetException
    0.34
     thuis
    0.33
    hyrchwyd
    0.33
    bufio
    0.31
    Activations Density 0.019%

    No Known Activations