© 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 EvalsExportsAPI 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. 12480
    Prev
    Next
    INDEX
    Explanations

    sections of code or data structures with significant lengths of whitespace or empty lines

    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
    SourceChecksum
    -0.82
     queſta
    -0.82
     BoxFit
    -0.74
     $_(
    -0.72
    jsonwebtoken
    -0.72
     ModelExpression
    -0.71
     ligiloj
    -0.70
     الحره
    -0.70
     وتسجيلات
    -0.69
     المعيارى
    -0.69
    POSITIVE LOGITS
    0.57
    6
    0.56
                
    0.51
    i
    0.42
     ejecutivo
    0.39
     Masyarakat
    0.39
     Internasional
    0.39
     Kebijakan
    0.38
    a
    0.38
     Keuangan
    0.38
    Activations Density 0.158%

    No Known Activations