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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 13396
    Prev
    Next
    INDEX
    Explanations

    references to proportions or ratios in relation to study results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.57
     Infórmanos
    -0.53
    PerformLayout
    -0.45
    ChildScrollView
    -0.44
    ніципалі
    -0.41
    balleur
    -0.41
    SourceChecksum
    -0.40
     Wicidata
    -0.40
    TProtocol
    -0.40
    ValueGenerated
    -0.37
    POSITIVE LOGITS
     half
    1.69
     thirds
    1.61
     third
    1.60
     quarter
    1.56
    thirds
    1.48
    third
    1.45
     helft
    1.44
    half
    1.40
     HALF
    1.36
     Drittel
    1.35
    Activations Density 0.643%

    No Known Activations