© 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. 15-GEMMASCOPE-RES-16K
    11. 1045
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evidence or demonstration of a hypothesis or finding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    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
    -0.54
     vac
    -0.53
    RenderAtEndOf
    -0.52
     Greet
    -0.51
     CRI
    -0.51
    IUrlHelper
    -0.49
    adpleegd
    -0.48
     bull
    -0.48
    uxxxx
    -0.48
     psu
    -0.48
    POSITIVE LOGITS
     avulla
    0.45
     these
    0.43
     zawsze
    0.42
    awsze
    0.41
     orejas
    0.41
     sillä
    0.41
    pośred
    0.40
     this
    0.40
     همیشه
    0.40
     każ
    0.40
    Activations Density 0.636%

    No Known Activations