© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 93074
    Prev
    Next
    INDEX
    Explanations

    content related to programming functions and their components, particularly in the context of dataframe structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `(**b**)` and `(b;`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.42
    ImageContext
    -0.39
     corne
    -0.34
    ParallelGroup
    -0.33
     CIL
    -0.32
     InputDecoration
    -0.32
     cang
    -0.31
     DAL
    -0.31
    StartTag
    -0.30
    Bit
    -0.30
    POSITIVE LOGITS
     b
    1.34
     getB
    1.07
     B
    1.07
    b
    0.99
     б
    0.96
    getB
    0.95
    B
    0.91
    ⓑ
    0.78
     ب
    0.74
    ⒝
    0.74
    Activations Density 0.490%

    No Known Activations