© 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. 36-GEMMASCOPE-RES-16K
    11. 12804
    Prev
    Next
    INDEX
    Explanations

    passages describing methods, components, or formulations related to scientific or technical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.49
    ViewFeatures
    -0.45
    Попис
    -0.44
    添
    -0.44
    AnchorStyles
    -0.41
    ccione
    -0.40
    pgm
    -0.40
    Tembelea
    -0.39
     ✭✭
    -0.38
    MessageTagHelper
    -0.37
    POSITIVE LOGITS
     consisting
    2.92
     consists
    2.77
     consisted
    2.64
     composed
    2.63
     consist
    2.53
     comprised
    2.53
     består
    2.23
     terdiri
    2.19
    composed
    2.14
     состоит
    2.09
    Activations Density 1.574%

    No Known Activations