© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8740
    Prev
    Next
    INDEX
    Explanations

    terms related to equity and compromise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.68
     disambiguazione
    -0.67
     Normdatei
    -0.57
     surla
    -0.55
    Референце
    -0.54
     Catawiki
    -0.53
     Réponses
    -0.53
    verwijspagina
    -0.52
    outSlope
    -0.52
     <>",
    -0.52
    POSITIVE LOGITS
     equity
    0.63
     curious
    0.61
     educational
    0.61
    equity
    0.58
     fiscal
    0.57
    Equity
    0.53
     Equity
    0.52
    attribute
    0.52
    curious
    0.52
     compromise
    0.51
    Activations Density 0.064%

    No Known Activations