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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 1058
    Prev
    Next
    INDEX
    Explanations

    data related to analysis and measurements, particularly in scientific or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -0.91
     is
    -0.81
     has
    -0.72
     istnieje
    -0.65
     znajduje
    -0.64
     isn
    -0.63
     wordt
    -0.63
     zależy
    -0.57
     έχει
    -0.56
     occurs
    -0.56
    POSITIVE LOGITS
     were
    2.39
    Were
    1.68
     Were
    1.53
    were
    1.51
     WERE
    1.32
     waren
    1.23
     weren
    1.22
     были
    1.19
     voltak
    1.16
     byli
    1.15
    Activations Density 1.070%

    No Known Activations