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. 1873
    Prev
    Next
    INDEX
    Explanations

    technical references to the "Boost" software library

    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
     Drey
    -0.74
    Na
    -0.69
    ne
    -0.65
     Richards
    -0.65
     san
    -0.61
    Karla
    -0.60
    aryen
    -0.60
    enem
    -0.60
     Watertown
    -0.59
    Richards
    -0.59
    POSITIVE LOGITS
     BOOST
    1.66
     Boost
    1.63
     boost
    1.52
    Boost
    1.47
    boost
    1.46
    BOOST
    1.41
     boosts
    1.34
     boosters
    1.32
     boosting
    1.24
     myſelf
    1.23
    Activations Density 0.023%

    No Known Activations