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. 5927
    Prev
    Next
    INDEX
    Explanations

    terms related to emergency response and medical directives

    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
    fjspx
    -0.69
    ]")]
    -0.60
    ItemBackground
    -0.57
    pyx
    -0.56
     GetEnumerator
    -0.56
     Wallflower
    -0.55
     Curiosity
    -0.55
    ]--;
    -0.54
     monthly
    -0.54
     weekly
    -0.54
    POSITIVE LOGITS
     emergency
    0.61
     plötzlich
    0.53
     неожидан
    0.53
     Emergency
    0.52
    emergency
    0.51
     contingency
    0.50
     scenarios
    0.49
     scenario
    0.48
     unexpected
    0.48
     sudden
    0.48
    Activations Density 0.381%

    No Known Activations