© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    specific numeric or code-based identifiers within a structured context, particularly related to skills or classifications

    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
    atoare
    -1.40
     braccia
    -1.39
     spalle
    -1.34
     esfuer
    -1.22
    ătoare
    -1.20
     gambe
    -1.16
     للمعارف
    -1.16
     sienta
    -1.16
     فريبيس
    -1.15
     encuentre
    -1.14
    POSITIVE LOGITS
     az
    0.58
     meg
    0.55
     k
    0.54
     ker
    0.53
     el
    0.52
     ny
    0.52
     fel
    0.50
     
    0.50
     nem
    0.50
     a
    0.49
    Activations Density 0.026%

    No Known Activations