Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1029
    Prev
    Next
    INDEX
    Explanations

    references to possessive pronouns and the entities they relate to

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

    Possessive pronouns: "its", "their," "her"

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and their followers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     někdo
    -0.30
    UrlResolution
    -0.29
     vuelva
    -0.29
     sosok
    -0.29
     geda
    -0.28
    isome
    -0.27
     rejo
    -0.27
     escalation
    -0.27
     лю
    -0.27
    include
    -0.26
    POSITIVE LOGITS
     own
    0.98
     owne
    0.75
     betweenstory
    0.71
     Own
    0.70
     eigenen
    0.68
    Own
    0.66
    selves
    0.66
     włas
    0.64
    自己的
    0.63
     nakalista
    0.63
    Activations Density 0.451%

    No Known Activations