© 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. 33-GEMMASCOPE-RES-16K
    11. 11444
    Prev
    Next
    INDEX
    Explanations

    discussions about common topics or objects, especially in a context related to importance or relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intenant
    -0.50
    setVerticalGroup
    -0.48
    RenderAtEndOf
    -0.41
    ckså
    -0.40
    TagMode
    -0.38
    évaluateur
    -0.38
     виправивши
    -0.38
     архивлан
    -0.37
    yntaxException
    -0.36
    UnusedPrivate
    -0.36
    POSITIVE LOGITS
     majority
    0.80
     average
    0.75
     term
    0.74
     meeste
    0.66
     typical
    0.65
    majority
    0.64
     act
    0.63
     popularity
    0.63
     mayoría
    0.63
     stereotypical
    0.61
    Activations Density 0.791%

    No Known Activations