© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2147
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related possessive constructions

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

    personal pronouns like "his" or "her".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     them
    -0.43
     betweenstory
    -0.40
     Lav
    -0.39
    .
    -0.39
     ка
    -0.38
     kah
    -0.37
     plate
    -0.37
     Lau
    -0.36
     note
    -0.36
     Note
    -0.36
    POSITIVE LOGITS
     Offisielt
    0.62
     whoſe
    0.60
     كومونز
    0.60
    berdayakan
    0.60
    mbalikan
    0.58
    whose
    0.58
    Personendaten
    0.57
     camiset
    0.56
     hänen
    0.56
    Ӕ
    0.55
    Activations Density 0.198%

    No Known Activations