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. 15-GEMMASCOPE-RES-16K
    6. 1667
    Prev
    Next
    INDEX
    Explanations

    conditional statements and null checks

    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
     مشين
    -0.79
     يتيمه
    -0.78
     GetEnumerator
    -0.77
    NewUrlParser
    -0.76
     Audiodateien
    -0.73
     חיצוניים
    -0.72
     Administrativna
    -0.70
    >",
    
    -0.70
    RegressionTest
    -0.69
     lenker
    -0.69
    POSITIVE LOGITS
     or
    1.42
     hoặc
    1.15
     atau
    1.01
    或者
    0.98
     или
    0.98
    或
    0.93
    Или
    0.92
    或者是
    0.92
     Или
    0.90
     eller
    0.88
    Activations Density 0.384%

    No Known Activations