© 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. 8580
    Prev
    Next
    INDEX
    Explanations

    contrastive phrases highlighting contradictions or unexpected outcomes

    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
     myö
    -0.33
     staff
    -0.30
    füh
    -0.29
     friend
    -0.29
     amigas
    -0.28
    คง
    -0.27
     certainly
    -0.27
    Certainly
    -0.26
     sicherlich
    -0.26
     Schließlich
    -0.26
    POSITIVE LOGITS
     للمعارف
    0.91
     ſtill
    0.78
     ब्रेकडाउन
    0.77
     resourceCulture
    0.77
     queſta
    0.76
     betweenstory
    0.72
     AssemblyTitle
    0.71
    RenderAtEndOf
    0.71
     gesteld
    0.71
     autorytatywna
    0.71
    Activations Density 0.356%

    No Known Activations