© 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. 0-GEMMASCOPE-RES-16K
    11. 7597
    Prev
    Next
    INDEX
    Explanations

    references to specific streets and avenues

    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
    DialogResult
    -0.49
     deſt
    -0.48
     محفوظة
    -0.47
    madonna
    -0.46
     الاطلاع
    -0.44
     ISO
    -0.43
    BagConstraints
    -0.43
     Inaug
    -0.42
     getOrder
    -0.42
    로운
    -0.41
    POSITIVE LOGITS
     rap
    0.82
    Rap
    0.80
     Rap
    0.79
     rape
    0.70
     raps
    0.69
     rapping
    0.69
    rap
    0.66
     RAP
    0.61
    RAP
    0.60
    rape
    0.60
    Activations Density 0.220%

    No Known Activations