© 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. 2135
    Prev
    Next
    INDEX
    Explanations

    references to people, particularly pronouns related to individuals and their relationships

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

    pronouns referring to people (especially "she", "he", "they", "you").

    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
     Tatsache
    -0.48
     spørs
    -0.41
     nemlig
    -0.41
     móvel
    -0.40
     húmedo
    -0.40
     avoient
    -0.39
     enfans
    -0.39
     dirait
    -0.39
     obiek
    -0.39
     miejsco
    -0.39
    POSITIVE LOGITS
     Tus
    0.58
     Bomber
    0.54
     Tuk
    0.54
     desired
    0.52
    IsMutable
    0.50
    ]="
    0.48
    tagHelperRunner
    0.48
     previously
    0.48
    =\""
    0.47
     Pele
    0.47
    Activations Density 0.228%

    No Known Activations