© 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. 11649
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to a variety of fields such as biology, law, and programming

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

    company or product names that start with "Cir" (like "Cirious").

    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
     lenker
    -0.48
     Hadley
    -0.46
    Попис
    -0.45
    Goed
    -0.45
    oare
    -0.44
    rénées
    -0.44
    ilée
    -0.43
    expressed
    -0.43
    ACHUSET
    -0.43
     Estuary
    -0.42
    POSITIVE LOGITS
     Cit
    0.44
    Cis
    0.44
    Cit
    0.44
     ci
    0.42
     Cis
    0.42
    ViewImports
    0.41
    CrossRef
    0.41
     InputDecoration
    0.41
    PerformLayout
    0.40
     jScrollPane
    0.40
    Activations Density 0.214%

    No Known Activations