© 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. 15-GEMMASCOPE-RES-16K
    11. 6036
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "new" in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
     ferons
    -0.56
     judiciaire
    -0.54
     présidenti
    -0.53
     pédagogique
    -0.52
     postępo
    -0.51
    agissait
    -0.50
     tänka
    -0.49
    attendre
    -0.49
     apparaît
    -0.49
    POSITIVE LOGITS
    EReference
    0.59
    Portail
    0.54
    Autoritní
    0.53
    Cyfarwyddwr
    0.50
     []*
    0.48
    EndProject
    0.47
    WithIOException
    0.46
    posedge
    0.44
    createElement
    0.43
    RTCK
    0.43
    Activations Density 0.138%

    No Known Activations