© 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. 15-GEMMASCOPE-RES-16K
    6. 2998
    Prev
    Next
    INDEX
    Explanations

    terms related to pediatric health and developmental disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kuliah
    -0.52
    ometrial
    -0.49
     Sart
    -0.48
    karna
    -0.48
    tagne
    -0.48
     Cell
    -0.47
    Isolation
    -0.47
     студент
    -0.47
    craper
    -0.47
    hely
    -0.46
    POSITIVE LOGITS
     children
    1.46
     childrens
    1.35
    children
    1.30
    Children
    1.28
     Children
    1.26
     child
    1.25
     kids
    1.20
    childrens
    1.19
     childs
    1.18
     CHILDREN
    1.17
    Activations Density 0.335%

    No Known Activations