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. 25-GEMMASCOPE-RES-16K
    6. 5692
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming operations, particularly around data insertion and retrieval in a database context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eleste
    -0.62
    ViewFeatures
    -0.60
     AssemblyCulture
    -0.57
    ContextHolder
    -0.53
     BeautifulSoup
    -0.50
    StructEnd
    -0.50
     '\\;'
    -0.50
    pirazione
    -0.49
     contextLoads
    -0.49
    ształ
    -0.48
    POSITIVE LOGITS
     adding
    2.21
     added
    2.18
     Adding
    2.16
    Adding
    2.11
    adding
    2.02
     addition
    2.01
     additions
    1.98
     Added
    1.98
     add
    1.96
    Added
    1.95
    Activations Density 0.715%

    No Known Activations