Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 16432
    Prev
    Next
    INDEX
    Explanations

    syntax elements and formatting in programming and markup languages

    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
    SequentialGroup
    -0.56
    lankton
    -0.50
    gamesh
    -0.49
     vastaan
    -0.48
     unterkunft
    -0.47
    jbl
    -0.47
     fulfilment
    -0.46
    vinfos
    -0.45
    toplankton
    -0.45
    цезда
    -0.45
    POSITIVE LOGITS
    noStroke
    0.43
     autorytatywna
    0.39
    RenderAtEndOf
    0.38
    webElement
    0.37
    RotationOrder
    0.36
     незавершена
    0.35
    PyExc
    0.35
    WriteTagHelper
    0.35
     MainAxisSize
    0.34
    Архівовано
    0.34
    Activations Density 0.099%

    No Known Activations