© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11635
    Prev
    Next
    INDEX
    Explanations

    references to processes and outcomes related to improvement or success through methods and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    setViewportView
    -0.60
     ogóle
    -0.57
    Initializable
    -0.52
     facie
    -0.51
     problemática
    -0.51
     toàn
    -0.47
    ViewImports
    -0.47
    ėms
    -0.47
    HtmlAttribute
    -0.47
     requisitos
    -0.46
    POSITIVE LOGITS
     judicious
    1.08
     careful
    1.07
     skillful
    1.02
     skilful
    0.96
     diligent
    0.94
     clever
    0.88
     proper
    0.85
     properly
    0.85
     concerted
    0.84
     having
    0.83
    Activations Density 0.590%

    No Known Activations