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. 11-GEMMASCOPE-RES-16K
    6. 5759
    Prev
    Next
    INDEX
    Explanations

    references to parameters in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '/';
    -0.79
    awtextra
    -0.76
     onCreateView
    -0.75
     Obr
    -0.72
    />";
    -0.71
     '!
    -0.71
     CONDU
    -0.69
     bson
    -0.67
     Uff
    -0.67
    خاذ
    -0.66
    POSITIVE LOGITS
     parameters
    1.58
     parameter
    1.47
     params
    1.47
     Parameters
    1.45
    params
    1.37
    Parameters
    1.34
    PARAM
    1.33
    parameters
    1.32
    Params
    1.32
     Param
    1.30
    Activations Density 0.100%

    No Known Activations