© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6898
    Prev
    Next
    INDEX
    Explanations

    attributes and descriptions of strength and resilience in a person, particularly focused on a maternal figure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Informal, colloquial language

    np_acts-logits-general · gemini-2.0-flash

    informal speech, slang, and contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sahiptir
    -0.68
     mnoho
    -0.61
    mektedir
    -0.54
    maktadır
    -0.53
    ējās
    -0.51
     deoarece
    -0.50
     diversas
    -0.50
    である
    -0.49
     geheel
    -0.49
     afstand
    -0.48
    POSITIVE LOGITS
     outta
    1.29
     dudes
    1.23
     gettin
    1.21
     gotta
    1.17
     fuckin
    1.16
     goin
    1.10
     lookin
    1.10
     gonna
    1.08
     talkin
    1.08
     fellas
    1.07
    Activations Density 0.426%

    No Known Activations