Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 7526
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly the closing of statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ImageContext
    -0.55
    +/**
    -0.53
    orf
    -0.51
     heil
    -0.50
    MODIFIED
    -0.48
    ╦
    -0.47
     Modified
    -0.46
    Vener
    -0.45
    껏
    -0.45
    uintptr
    -0.44
    POSITIVE LOGITS
     متعلقه
    0.79
    findpost
    0.78
     مشين
    0.76
    WaitGroup
    0.72
    })));
    0.67
     defaultstate
    0.67
     StatefulWidget
    0.66
     kasarigan
    0.65
    CppCodeGen
    0.65
    তথ্যসূত্র
    0.63
    Activations Density 0.118%

    No Known Activations