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. 13-GEMMASCOPE-RES-16K
    6. 321
    Prev
    Next
    INDEX
    Explanations

    specific terms related to health, particularly in the context of risk and effect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "especially" and phrases following it with high emphasis or importance.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lsz
    -0.52
    <caption>
    -0.52
     continúas
    -0.51
     tito
    -0.49
    stoppable
    -0.48
    Филь
    -0.47
    ReturnValue
    -0.47
    ceans
    -0.47
    ([...
    -0.45
     Pompe
    -0.45
    POSITIVE LOGITS
     Particularly
    1.15
     especially
    1.08
     particularly
    1.08
     Especially
    1.06
    Especially
    1.05
    particularly
    1.02
    especially
    1.00
     terutama
    0.94
     particularmente
    0.92
     Особенно
    0.91
    Activations Density 0.396%

    No Known Activations