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. 22-GEMMASCOPE-RES-16K
    6. 10396
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal circumstances and decisions regarding relationships and parenthood

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

    Reflexive pronouns and possessives

    np_acts-logits-general · gemini-2.0-flash

    self reference or personal pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.74
     autorytatywna
    -0.68
     invokingState
    -0.67
     gynhyrchwyd
    -0.64
     Meksiku
    -0.64
    Referencies
    -0.62
    Chham
    -0.61
    лтамалар
    -0.61
     незавершена
    -0.59
     تضيفلها
    -0.56
    POSITIVE LOGITS
     oneself
    1.76
     your
    0.93
     eigenen
    0.90
     she
    0.88
     propria
    0.83
    your
    0.82
     soi
    0.82
    ones
    0.82
    she
    0.79
     her
    0.79
    Activations Density 0.528%

    No Known Activations