© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9913
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to emotional experiences and human interactions

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

    third-person references, especially possessive “their/her” phrases and the key noun or verb that immediately follows them.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    possessive pronouns ("their", "her") followed by nouns, particularly when describing activities, attributes, or possessions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    Personensuche
    -0.43
    cerpt
    -0.43
     meus
    -0.43
     myself
    -0.42
     mój
    -0.42
    spection
    -0.41
    了我
    -0.40
     Autorisations
    -0.39
     withRouter
    -0.39
    naeus
    -0.39
    POSITIVE LOGITS
    Their
    0.82
    their
    0.76
     Their
    0.75
     themselves
    0.70
    他們的
    0.67
    themselves
    0.66
     their
    0.63
    他们的
    0.63
     THEIR
    0.62
     ihrer
    0.60
    Activations Density 0.418%

    No Known Activations