© 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. 17-GEMMASCOPE-RES-16K
    6. 5357
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their biographical information

    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
     husbands
    -0.79
     husband
    -0.78
     wives
    -0.66
    Husband
    -0.65
    husband
    -0.64
     Mujer
    -0.61
     chồng
    -0.61
     wife
    -0.61
     married
    -0.60
     мужа
    -0.60
    POSITIVE LOGITS
     child
    1.14
     CHILD
    1.12
     juvenile
    1.10
     Child
    1.08
     Childhood
    1.08
    child
    1.08
     Juvenile
    1.07
     childhood
    1.06
     kid
    1.05
     pediatric
    1.04
    Activations Density 0.516%

    No Known Activations