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. 10-GEMMASCOPE-RES-16K
    6. 13183
    Prev
    Next
    INDEX
    Explanations

    phrases related to age and personal identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Familienname
    -0.57
     Wikispecies
    -0.55
     signora
    -0.54
     retired
    -0.48
    Retired
    -0.48
    uxxxx
    -0.48
    retired
    -0.45
     husband
    -0.45
     Retired
    -0.45
    太太
    -0.44
    POSITIVE LOGITS
     youth
    1.20
     teens
    1.12
     student
    1.09
     teenage
    1.07
     youths
    1.06
     teenagers
    1.06
     adolescent
    1.06
     Youth
    1.05
     giovan
    1.05
     adolescence
    1.04
    Activations Density 0.482%

    No Known Activations