Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 2010
    Prev
    Next
    INDEX
    Explanations

    references to the concept of evolution and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gef
    -0.58
     Sagittarius
    -0.56
    chiat
    -0.56
    ocardium
    -0.55
     Jeanette
    -0.54
     Hang
    -0.53
    aliers
    -0.53
    projec
    -0.52
     Setting
    -0.52
    esgue
    -0.51
    POSITIVE LOGITS
     ev
    0.80
    tagext
    0.80
     Савезне
    0.77
    DockStyle
    0.73
    findpost
    0.70
     evo
    0.70
    Ev
    0.69
     AssemblyVersion
    0.68
    parsedMessage
    0.68
     EVOLUTION
    0.68
    Activations Density 0.146%

    No Known Activations