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. 0-GEMMASCOPE-RES-16K
    6. 9867
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to human rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.83
     ویکی‌پدیا
    -0.74
     reconna
    -0.71
    accepte
    -0.69
    Personendaten
    -0.69
     suffit
    -0.68
    multirow
    -0.68
     initComponents
    -0.68
    IsContent
    -0.68
    __':
    -0.67
    POSITIVE LOGITS
     déclaration
    0.57
     lung
    0.56
     fucking
    0.56
     blame
    0.56
     diritti
    0.55
     rights
    0.55
     declare
    0.53
     declaration
    0.53
     mierda
    0.53
    cols
    0.52
    Activations Density 0.103%

    No Known Activations