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. 8653
    Prev
    Next
    INDEX
    Explanations

    terms related to business expansion and growth strategies

    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
    ómicos
    -0.55
    +#+
    -0.50
    реб
    -0.50
    ujudkan
    -0.49
    IndentedString
    -0.49
    <!--[
    -0.47
    CDATA
    -0.47
    TRAILING
    -0.46
    buttonBar
    -0.46
    Réalisation
    -0.45
    POSITIVE LOGITS
     expanded
    1.98
     expand
    1.97
     expanding
    1.92
     expansion
    1.88
     expands
    1.88
     Expanding
    1.81
    Expanding
    1.73
     broaden
    1.71
     Expand
    1.71
     Expansion
    1.69
    Activations Density 0.632%

    No Known Activations