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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11508
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to individuals, particularly "he" and "she."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorisations
    -0.57
     Uniti
    -0.54
    seamnă
    -0.53
    OLIS
    -0.52
     parseFrom
    -0.52
    UIControlState
    -0.51
     Photocase
    -0.50
     Pria
    -0.50
    PLEX
    -0.49
     RoutedEventArgs
    -0.49
    POSITIVE LOGITS
    hehe
    0.82
    俩
    0.73
    He
    0.72
    hehehe
    0.72
    ineno
    0.68
    meneu
    0.66
    ://$
    0.63
    eding
    0.62
    he
    0.62
    His
    0.62
    Activations Density 0.225%

    No Known Activations