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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10359
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure elements and packages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }</
    -0.56
    ->_
    -0.52
     melden
    -0.51
    forge
    -0.51
     makro
    -0.46
    }></
    -0.46
     Sena
    -0.46
    OUTPUT
    -0.46
    scriptcase
    -0.46
    hdys
    -0.45
    POSITIVE LOGITS
    Autoritní
    0.76
    astify
    0.73
     تضيفلها
    0.71
     resourceCulture
    0.68
     propOrder
    0.68
    Dislikes
    0.63
    цездатний
    0.63
    таратура
    0.60
    postsleuth
    0.59
    Parcelize
    0.58
    Activations Density 0.029%

    No Known Activations