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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2887
    Prev
    Next
    INDEX
    Explanations

    code-related elements, specifically function calls and variable manipulations within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.49
     or
    -0.47
    ling
    -0.42
    /
    -0.39
    aban
    -0.39
     
    -0.39
    ba
    -0.38
    zeuge
    -0.37
     co
    -0.37
    Qu
    -0.37
    POSITIVE LOGITS
     للاسماء
    0.97
     typelib
    0.89
    RectangleBorder
    0.88
    Personendaten
    0.86
    ++
    
    0.84
     }}"></
    0.82
    الإنجليزية
    0.81
    曖昧さ回避
    0.80
    mybatisplus
    0.79
     ujednoznacz
    0.78
    Activations Density 0.217%

    No Known Activations