© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8795
    Prev
    Next
    INDEX
    Explanations

    terms related to support for medical research and fundraising activities

    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
    Xna
    -0.61
    jooq
    -0.60
    AddHtmlAttribute
    -0.55
    oliber
    -0.54
     springfox
    -0.52
    nestjs
    -0.51
     Polsek
    -0.50
    ặt
    -0.49
     esercit
    -0.49
     الفلك
    -0.48
    POSITIVE LOGITS
     cancer
    0.91
    cancer
    0.86
    Cure
    0.85
    Cancer
    0.85
     kanker
    0.83
     charity
    0.83
     Cancer
    0.81
     Cure
    0.76
     fundraising
    0.76
     charities
    0.76
    Activations Density 0.227%

    No Known Activations