© 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. 23-GEMMASCOPE-RES-16K
    11. 9503
    Prev
    Next
    INDEX
    Explanations

    references to participation or engagement in a community or collective context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alike
    -0.53
    IKit
    -0.53
    RegistryLite
    -0.50
     Administrativna
    -0.48
    IntOverflow
    -0.48
    nloa
    -0.47
    JspWriter
    -0.47
    ništvo
    -0.47
    новништво
    -0.46
    convex
    -0.45
    POSITIVE LOGITS
     permanent
    1.57
     permanently
    1.36
    permanent
    1.34
    Permanent
    1.30
     Permanent
    1.27
     PERMAN
    1.24
     permanente
    1.20
    perman
    1.12
     perman
    1.08
     permanentes
    1.08
    Activations Density 0.860%

    No Known Activations