© 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. 37-GEMMASCOPE-RES-16K
    11. 8434
    Prev
    Next
    INDEX
    Explanations

    references to various surfaces in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.49
    saraba
    -0.41
     اعت
    -0.36
    PROLOG
    -0.34
     krę
    -0.34
    nictví
    -0.34
    Gweler
    -0.34
     toiminta
    -0.32
    товано
    -0.32
    úgó
    -0.31
    POSITIVE LOGITS
     surface
    3.98
    surface
    3.44
     Surface
    3.42
     SURFACE
    3.28
    Surface
    3.28
     surfaces
    3.11
    SURFACE
    2.91
     superficie
    2.73
     superfície
    2.73
     Surfaces
    2.64
    Activations Density 1.033%

    No Known Activations