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. 15-GEMMASCOPE-RES-16K
    6. 1652
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to health and medical conditions

    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
    LookAnd
    -0.67
    Brainz
    -0.56
    DateTimeField
    -0.49
     sekal
    -0.48
    Kaieteur
    -0.47
     NgModule
    -0.46
     aufgenommen
    -0.44
    :✨
    -0.44
    IEnumerator
    -0.44
    商品説明
    -0.43
    POSITIVE LOGITS
     how
    1.00
    XmlAccessType
    0.86
     why
    0.79
     related
    0.75
    how
    0.72
     its
    0.72
     relativi
    0.71
     what
    0.70
    related
    0.64
     relation
    0.63
    Activations Density 0.281%

    No Known Activations