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. 23-GEMMASCOPE-RES-131K
    6. 23121
    Prev
    Next
    INDEX
    Explanations

    instances of object construction and builder patterns in programming code

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certain
    -0.50
    :
    -0.47
    addGap
    -0.46
    <bos>
    -0.45
    ===============
    -0.45
    æs
    -0.43
     toată
    -0.42
    TypeOf
    -0.42
     faptul
    -0.42
     topik
    -0.42
    POSITIVE LOGITS
     builder
    1.40
     Builder
    1.38
    Builder
    1.26
    builder
    1.24
     builders
    1.16
     Builders
    1.13
    builders
    1.02
     BUILD
    1.02
    Builders
    0.94
    FieldBuilder
    0.93
    Activations Density 0.003%

    No Known Activations