© 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. 30-GEMMASCOPE-RES-16K
    11. 9976
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    hard to imagine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __((
    -0.65
     poveznice
    -0.54
    MENAFN
    -0.45
     كومونز
    -0.44
    /*
    -0.44
    //
    -0.43
    enumi
    -0.43
    forName
    -0.42
    الحياه
    -0.42
    uxxxx
    -0.41
    POSITIVE LOGITS
     shock
    1.52
     shocked
    1.50
     SHOCK
    1.30
     stunned
    1.28
     Shock
    1.27
     astonishment
    1.24
     astonished
    1.24
     disbelief
    1.23
     amazement
    1.23
     shocks
    1.21
    Activations Density 0.225%

    No Known Activations