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. 12-GEMMASCOPE-RES-16K
    6. 12293
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to inequalities and logarithmic functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Speicher
    -0.85
     OFDb
    -0.74
     Pinch
    -0.73
    RenderAtEndOf
    -0.70
    PMailer
    -0.70
    abestanden
    -0.70
    }{*}{}
    -0.70
    bigsqcup
    -0.69
    ----</
    -0.69
    Bronnen
    -0.66
    POSITIVE LOGITS
     Rhy
    0.82
    seamnă
    0.82
     Gwyn
    0.80
    ConstraintMaker
    0.75
     препратки
    0.75
    Rightarrow
    0.74
    Leftrightarrow
    0.71
     Hélène
    0.69
     Maruti
    0.69
    seteq
    0.69
    Activations Density 0.501%

    No Known Activations