© 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. 15-GEMMASCOPE-RES-16K
    11. 2927
    Prev
    Next
    INDEX
    Explanations

    interrogative or modal expressions and statements involving identity or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.71
     geſch
    -0.66
     pinulongan
    -0.65
     témoig
    -0.65
    WriteLiteral
    -0.63
     ***!
    -0.61
     müſſen
    -0.61
    ynb
    -0.60
     дописавши
    -0.60
    нгред
    -0.59
    POSITIVE LOGITS
     elástico
    0.33
    MoveNext
    0.30
     propiedad
    0.30
    UrlResolution
    0.29
     ejecutivo
    0.29
     infraestructura
    0.29
    Története
    0.28
     efficaces
    0.28
     onlyOwner
    0.28
     universelle
    0.27
    Activations Density 0.375%

    No Known Activations