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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 1918
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity for dedicated funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trotzdem
    -0.62
     Enfin
    -0.58
     nevertheless
    -0.57
    もしれません
    -0.56
     Dennoch
    -0.55
    Enfin
    -0.54
     Anyways
    -0.54
     unknownFields
    -0.53
    今後も
    -0.53
    still
    -0.53
    POSITIVE LOGITS
    为此
    1.23
    Dazu
    1.10
     Dafür
    1.00
    Ideally
    0.97
     daarvoor
    0.96
     Ideally
    0.93
    Fortunately
    0.87
     Dazu
    0.86
     hierfür
    0.85
    Luckily
    0.84
    Activations Density 0.404%

    No Known Activations