© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 4110
    Prev
    Next
    INDEX
    Explanations

    terms related to acquisition and obtaining ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁴
    -0.66
     말
    -0.58
    ğiniz
    -0.57
     ModelExpression
    -0.57
     Administrativna
    -0.55
    reactstrap
    -0.54
    urably
    -0.53
     PagesJaunes
    -0.53
     noastre
    -0.52
    webElementXpaths
    -0.52
    POSITIVE LOGITS
     fold
    0.57
     conference
    0.54
     Park
    0.53
     park
    0.52
     moment
    0.48
    Park
    0.47
     kinetic
    0.46
     PARK
    0.44
    park
    0.43
    dk
    0.42
    Activations Density 0.182%

    No Known Activations