© 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. 34-GEMMASCOPE-RES-16K
    11. 3164
    Prev
    Next
    INDEX
    Explanations

    negations and conditions in code or logic statements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nicht
    -0.56
     not
    -0.52
    rawDesc
    -0.52
     bukan
    -0.49
     não
    -0.47
    IndexOf
    -0.47
    InputBorder
    -0.46
     tidak
    -0.45
    ไม่ได้
    -0.43
    FormTagHelper
    -0.42
    POSITIVE LOGITS
    VersionUID
    0.50
     NUKAT
    0.47
     yet
    0.44
    addContainerGap
    0.44
    //
    0.44
    \{\\
    0.42
    iniums
    0.41
    ांकि
    0.40
     OFDb
    0.40
    tagHelperRunner
    0.40
    Activations Density 0.091%

    No Known Activations