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. 12827
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to calculus and functional analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    aarrggbb
    -0.74
    towane
    -0.53
    imantan
    -0.51
     '\\;'
    -0.50
    ingga
    -0.49
    mutter
    -0.47
     Cap
    -0.47
    ranging
    -0.47
     tiros
    -0.46
    úrese
    -0.46
    POSITIVE LOGITS
    зулта
    0.64
    URLException
    0.64
    hoeddwyd
    0.59
     $+\
    0.58
     $-\
    0.57
     useStyles
    0.56
    UserScript
    0.53
     "','
    0.53
     Shakspeare
    0.53
    jenost
    0.53
    Activations Density 0.867%

    No Known Activations