© 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. 31-GEMMASCOPE-RES-16K
    11. 13303
    Prev
    Next
    INDEX
    Explanations

    references to potential plans or projects related to infrastructure or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to future plans, proposals, and intended actions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recently
    -0.68
     lately
    -0.60
     recent
    -0.59
     recente
    -0.58
     recientemente
    -0.58
    recently
    -0.57
     reciente
    -0.56
     Recently
    -0.56
    recent
    -0.55
     almost
    -0.54
    POSITIVE LOGITS
     possibly
    1.05
    possibly
    1.02
     someday
    1.00
     Possibly
    0.98
     eventuell
    0.96
    Possibly
    0.93
     preferably
    0.89
     possible
    0.87
     eventual
    0.86
    preferably
    0.85
    Activations Density 0.946%

    No Known Activations