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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 17-GEMMASCOPE-RES-16K
    6. 10872
    Prev
    Next
    INDEX
    Explanations

    words associated with medical treatments and biological responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.74
    abestanden
    -0.73
     Biôgrafia
    -0.68
     متعلقه
    -0.65
     Paglinawan
    -0.64
    </thead>
    -0.64
     aceptas
    -0.64
    enumi
    -0.62
    ()]);
    -0.62
    tvguidetime
    -0.60
    POSITIVE LOGITS
     helps
    1.15
     help
    0.95
     provides
    0.92
     helped
    0.88
    helps
    0.87
     membantu
    0.86
     gives
    0.86
    ช่วย
    0.84
     Helps
    0.83
     enables
    0.81
    Activations Density 0.765%

    No Known Activations