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. 12257
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to gene annotation and sequencing techniques

    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
     protoimpl
    -0.72
    новниш
    -0.71
     NSCoder
    -0.70
    StoryboardSegue
    -0.66
    PerformLayout
    -0.63
    thenia
    -0.62
     pinulongan
    -0.60
     XCTest
    -0.60
    astify
    -0.59
    escar
    -0.58
    POSITIVE LOGITS
    toMatch
    0.47
    relsen
    0.45
     raw
    0.44
     mxArray
    0.44
    scriptId
    0.43
     qu
    0.43
    tigem
    0.43
     feature
    0.43
    Resolved
    0.42
     multi
    0.42
    Activations Density 2.735%

    No Known Activations