© 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. 7709
    Prev
    Next
    INDEX
    Explanations

    phrases related to recovery and restoration themes

    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
    endpush
    -0.36
     contraire
    -0.35
    Defined
    -0.33
     proportional
    -0.31
     ölüm
    -0.30
     glä
    -0.30
     envy
    -0.29
    慷
    -0.29
    namiento
    -0.29
    assment
    -0.28
    POSITIVE LOGITS
     damaged
    1.75
     broken
    1.59
     lost
    1.54
     injured
    1.53
    damaged
    1.48
     fallen
    1.45
     shattered
    1.42
     ailing
    1.41
     Damaged
    1.40
     ruined
    1.39
    Activations Density 1.222%

    No Known Activations