© 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. 3-GEMMASCOPE-RES-16K
    11. 8498
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores or placeholders in code or configuration files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.38
     Gelegenheit
    -0.33
     hakkında
    -0.33
     perdere
    -0.32
     surpresa
    -0.32
     Escribe
    -0.32
     kommenden
    -0.31
     Vergrößern
    -0.30
     alrededores
    -0.30
     tamamen
    -0.30
    POSITIVE LOGITS
    MessageOf
    0.97
    +#+
    0.88
     kasarigan
    0.82
    aarrggbb
    0.75
    oredCriteria
    0.73
    ########.
    0.73
    protoimpl
    0.72
     propOrder
    0.68
    XmlAccessorType
    0.67
     EconPapers
    0.64
    Activations Density 0.560%

    No Known Activations