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. 22-GEMMASCOPE-RES-16K
    6. 7921
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to salivary glands and oral conditions

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

    the mouth and saliva

    np_acts-logits-general · gemini-2.0-flash

    oral cavity and saliva

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.71
    Enllaces
    -0.61
    SBATCH
    -0.61
     Réponses
    -0.60
    ContentAsync
    -0.58
     wireType
    -0.57
     kaynağından
    -0.55
    انجليز
    -0.54
     Bein
    -0.54
    principalTable
    -0.54
    POSITIVE LOGITS
     mouth
    1.78
     Mouth
    1.64
    mouth
    1.49
     tongue
    1.49
    Mouth
    1.43
     saliva
    1.33
     oral
    1.32
     mouths
    1.32
     lips
    1.32
     Oral
    1.28
    Activations Density 0.488%

    No Known Activations