© 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. 38-GEMMASCOPE-RES-16K
    11. 13692
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance, distinction, or recognition within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.53
     one
    -0.48
    eseorang
    -0.46
     nonUne
    -0.45
    ///</
    -0.43
     дописавши
    -0.43
     second
    -0.42
     kasarigan
    -0.41
    Архівовано
    -0.41
     doInBackground
    -0.41
    POSITIVE LOGITS
     few
    1.09
     many
    1.03
    Few
    0.94
    few
    0.93
     wenigen
    0.91
    many
    0.90
    Many
    0.85
     MANY
    0.82
    MANY
    0.82
     reasons
    0.81
    Activations Density 0.252%

    No Known Activations