© 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. 0-GEMMASCOPE-RES-16K
    11. 320
    Prev
    Next
    INDEX
    Explanations

    terms related to peaks or high points in data or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hObject
    -0.37
    ♥♥
    -0.36
    record
    -0.33
    ValueStyle
    -0.33
     libr
    -0.33
    ●●
    -0.32
    ++++++++++++++++
    -0.32
     carre
    -0.31
    Web
    -0.31
     gand
    -0.31
    POSITIVE LOGITS
     confuses
    0.81
     confuse
    0.80
     confusion
    0.78
     confused
    0.78
     confuso
    0.76
     Confused
    0.76
     peak
    0.74
    confusion
    0.73
     confusión
    0.72
     Confusion
    0.71
    Activations Density 0.187%

    No Known Activations