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. 20-GEMMASCOPE-RES-16K
    6. 6676
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and their respective class structures

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

    following "java.lang"

    np_acts-logits-general · gemini-2.0-flash

    java.lang and language attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.85
    }');
    -0.77
    erweise
    -0.77
    MigrationBuilder
    -0.75
    ']))
    
    -0.71
    SharedDtor
    -0.71
     typelib
    -0.69
    __':
    -0.68
     gynhyrchwyd
    -0.68
    MessageOf
    -0.67
    POSITIVE LOGITS
     Lang
    0.67
    Lang
    0.57
    lang
    0.56
     LANG
    0.55
    nd
    0.50
     Langley
    0.49
    ofing
    0.48
     lang
    0.48
    llary
    0.46
    reflect
    0.46
    Activations Density 0.039%

    No Known Activations