© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14987
    Prev
    Next
    INDEX
    Explanations

    expressions and reactions indicative of shock or surprise

    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
     defaultstate
    -0.70
    queryInterface
    -0.59
     AssemblyVersion
    -0.54
    ngdoc
    -0.53
    تقاوى
    -0.53
    __((
    -0.51
     getItemCount
    -0.50
    tvguidetime
    -0.50
    contentLoaded
    -0.49
     ContentValues
    -0.49
    POSITIVE LOGITS
     shocked
    1.67
     stunned
    1.63
     shock
    1.56
     dumbfounded
    1.42
     astonished
    1.42
    shock
    1.32
    shocked
    1.28
     Shock
    1.27
     astonishment
    1.27
    Shock
    1.27
    Activations Density 0.335%

    No Known Activations