© 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. 7364
    Prev
    Next
    INDEX
    Explanations

    warnings and alerts related to potential risks or hazards

    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
    ExecuteReader
    -0.35
    szönöm
    -0.35
    BagLayout
    -0.33
    VIAF
    -0.31
     bezeichneter
    -0.31
    awtextra
    -0.31
     orgull
    -0.30
    ährend
    -0.29
    InlineData
    -0.28
     naer
    -0.28
    POSITIVE LOGITS
     warning
    3.36
     warnings
    3.05
     warn
    2.86
     Warning
    2.86
     warned
    2.75
    warning
    2.69
     warns
    2.64
    Warning
    2.59
     Warnings
    2.53
     WARNING
    2.52
    Activations Density 0.523%

    No Known Activations