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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10112
    Prev
    Next
    INDEX
    Explanations

    references to the color green and its applications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.83
    Personensuche
    -0.79
     Roskov
    -0.79
    IUrlHelper
    -0.77
    *{-
    -0.77
     OMITBAD
    -0.76
    RegistryLite
    -0.74
     виправивши
    -0.74
     FirebaseAuth
    -0.74
    />,
    -0.72
    POSITIVE LOGITS
     green
    1.14
     Green
    1.12
    Green
    1.09
     GREEN
    1.03
    green
    0.99
    GREEN
    0.98
     greener
    0.97
     greens
    0.93
    Greens
    0.87
     Greens
    0.86
    Activations Density 0.107%

    No Known Activations