© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106060
    Prev
    Next
    INDEX
    Explanations

    dashes or hyphens used in a context that denotes a range or connection between items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     außerdem
    -0.40
     además
    -0.39
     Verordnung
    -0.39
     lisäksi
    -0.37
     Außerdem
    -0.37
     have
    -0.37
     Wissenschaft
    -0.36
     provided
    -0.36
     peuples
    -0.36
     Gemeinschaft
    -0.35
    POSITIVE LOGITS
    complexContent
    0.74
     Audiodateien
    0.68
     noDo
    0.66
     Roskov
    0.65
     Numerade
    0.62
     gynhyrchwyd
    0.62
     &___
    0.61
    帖最后由
    0.61
     Exacts
    0.60
     ब्रेकडाउन
    0.60
    Activations Density 0.057%

    No Known Activations