© 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. 38-GEMMASCOPE-RES-16K
    11. 15893
    Prev
    Next
    INDEX
    Explanations

    requests for help or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.53
    おめでとうございます
    -0.49
    XtraBars
    -0.46
     Efq
    -0.46
    intenant
    -0.46
     lizenzfreie
    -0.44
     Voss
    -0.44
     proposons
    -0.43
     насељу
    -0.42
     MainAxisSize
    -0.41
    POSITIVE LOGITS
     appreciate
    2.23
     appreciated
    2.19
     Appreciate
    2.00
     appreciation
    2.00
     appreciates
    1.90
     appreciating
    1.84
    Appreciate
    1.80
     Appreciation
    1.75
    appreciated
    1.70
     apreci
    1.68
    Activations Density 0.240%

    No Known Activations