© 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. 106033
    Prev
    Next
    INDEX
    Explanations

    underscores preceding words or identifiers, indicating a focus on variable or function names

    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
     ivelany
    -0.44
     Ceramby
    -0.40
     additionally
    -0.39
    Datuak
    -0.38
    getInventory
    -0.38
    lepiej
    -0.37
     angekommen
    -0.37
     declared
    -0.37
     are
    -0.36
    それが
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.64
    RenderAtEndOf
    0.60
     noDo
    0.54
    ̈́
    0.53
     CreateTagHelper
    0.53
    tagPool
    0.49
     ErrIntOverflow
    0.49
    躇
    0.48
    conce
    0.47
     gynhyrchwyd
    0.47
    Activations Density 0.059%

    No Known Activations