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. 17-GEMMASCOPE-RES-16K
    6. 7212
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating possession or references to individuals in a personal context

    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
    setVerticalGroup
    -0.70
    cdef
    -0.57
    ChildScrollView
    -0.55
    PreferredItem
    -0.55
    ]='\
    -0.55
    AttributedString
    -0.55
    ?>">
    -0.55
    exitRule
    -0.54
    ngdoc
    -0.54
    Subviews
    -0.54
    POSITIVE LOGITS
     benefit
    1.23
     behalf
    1.14
    benefit
    1.04
    Benefit
    0.96
     Benefit
    0.94
     BENE
    0.83
     beneficio
    0.75
     sake
    0.74
     detriment
    0.73
     advantage
    0.72
    Activations Density 0.222%

    No Known Activations