© 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. 40-GEMMASCOPE-RES-16K
    11. 3338
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes and methods in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élector
    -0.44
    Meetings
    -0.42
     ब्रेकडाउन
    -0.41
     Meetings
    -0.41
    AddHtmlAttribute
    -0.39
     Audiodateien
    -0.39
    meetings
    -0.38
    unteer
    -0.38
     Concerts
    -0.38
    enterOuterAlt
    -0.37
    POSITIVE LOGITS
     operation
    1.48
     procedure
    1.34
     task
    1.21
     exercise
    1.13
    opération
    1.07
     maneuver
    1.04
    operation
    1.04
     opération
    1.03
     manoeuvre
    1.02
     action
    0.98
    Activations Density 1.609%

    No Known Activations