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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1838
    Prev
    Next
    INDEX
    Explanations

    technical terms and classes related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.73
    writeFieldEnd
    -0.66
     beginnetje
    -0.58
    ],"
    -0.56
    Pyx
    -0.56
    ParallelGroup
    -0.55
     *>(
    -0.52
    Portály
    -0.51
     Pre
    -0.51
    SequentialGroup
    -0.51
    POSITIVE LOGITS
    chyma
    0.52
     RSSSF
    0.51
     Poincar
    0.50
    MessageTagHelper
    0.50
     становника
    0.49
    gameserver
    0.49
     unauthorised
    0.48
    ;
    0.48
     Légion
    0.48
     geweest
    0.48
    Activations Density 0.142%

    No Known Activations