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. 14-GEMMASCOPE-RES-16K
    6. 12905
    Prev
    Next
    INDEX
    Explanations

    various types of headgear and head-related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RIVERS
    -0.63
    cise
    -0.62
     vân
    -0.61
     dịch
    -0.61
     deere
    -0.61
    thington
    -0.60
     Reynolds
    -0.60
     Secund
    -0.59
    кти
    -0.59
     Rivers
    -0.59
    POSITIVE LOGITS
     hats
    1.35
     Hats
    1.09
    Hats
    1.07
     hat
    1.05
     helmet
    1.02
     chapeau
    0.99
     roof
    0.98
     helmets
    0.97
    Hat
    0.93
    帽子
    0.93
    Activations Density 0.505%

    No Known Activations