© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14525
    Prev
    Next
    INDEX
    Explanations

    numbers and their relationships in a structured form, such as statistical data or quantitative measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.95
    Portale
    -0.83
    ритори
    -0.79
    Демографія
    -0.78
     betweenstory
    -0.68
    mallows
    -0.68
    ografija
    -0.67
     ModelExpression
    -0.67
     endforeach
    -0.67
    tagext
    -0.66
    POSITIVE LOGITS
    .
    0.47
     but
    0.44
     is
    0.43
     man
    0.43
    -
    0.43
     shorter
    0.40
     kaynağından
    0.40
     for
    0.39
     recenti
    0.39
     can
    0.39
    Activations Density 2.254%

    No Known Activations