© 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. 34-GEMMASCOPE-RES-16K
    11. 13374
    Prev
    Next
    INDEX
    Explanations

    references to specific inventions or products along with their historical context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     asesinado
    -0.88
     pagado
    -0.86
     cumplido
    -0.85
     prohibido
    -0.81
     escuchado
    -0.79
     mijne
    -0.79
     Masyarakat
    -0.76
     Kebijakan
    -0.76
     Keuangan
    -0.75
     kysy
    -0.75
    POSITIVE LOGITS
    <unused41>
    1.12
    <unused43>
    1.11
    <unused20>
    1.11
    <pad>
    1.10
    <unused17>
    1.10
    <unused28>
    1.09
    <unused40>
    1.09
    <unused7>
    1.09
    [@BOS@]
    1.09
    <unused3>
    1.09
    Activations Density 0.073%

    No Known Activations