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. 5-GEMMASCOPE-RES-16K
    6. 12816
    Prev
    Next
    INDEX
    Explanations

    references to various art forms and their related academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.71
    mybatis
    -0.68
    mobileqq
    -0.68
    setDo
    -0.67
     CYTHON
    -0.67
    ghalaya
    -0.67
    Sdk
    -0.66
     הנ
    -0.65
    oredCriteria
    -0.65
    VersionUID
    -0.64
    POSITIVE LOGITS
     Arts
    1.84
     arts
    1.71
    Arts
    1.62
     ARTS
    1.57
    arts
    1.17
    ARTS
    1.05
    ."</
    0.99
    ^(@)
    0.89
    />";
    0.89
    .";
    
    0.86
    Activations Density 0.086%

    No Known Activations