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 - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12273
    Prev
    Next
    INDEX
    Explanations

    parentheses and their associated control flow statements in programming code

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

    Code blocks' opening parentheses followed by exception types

    np_acts-logits-general · gemini-2.0-flash

    Java exception handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -0.47
    sendStatus
    -0.46
    един
    -0.45
     señ
    -0.43
     terbesar
    -0.42
    жу
    -0.41
     rojas
    -0.40
     belonging
    -0.39
    sekret
    -0.38
     à
    -0.38
    POSITIVE LOGITS
     Administrativna
    0.94
    IndentedString
    0.94
     للاسماء
    0.92
     protoimpl
    0.87
     /\.
    0.87
     /\.(
    0.85
    ✨:
    0.82
    matchCondition
    0.80
    hyrchwyd
    0.79
     الحره
    0.78
    Activations Density 0.022%

    No Known Activations