© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4318
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their relationships

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

    The pronoun "his" or "him"

    np_acts-logits-general · gemini-2.0-flash

    male pronoun usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ihrem
    -0.82
     ihren
    -0.76
     internetowa
    -0.75
     koja
    -0.73
     ihrer
    -0.71
     herself
    -0.70
     ihre
    -0.69
     која
    -0.65
     została
    -0.62
    ступила
    -0.61
    POSITIVE LOGITS
     himself
    2.40
    himself
    1.97
     his
    1.95
    his
    1.74
     Himself
    1.57
    His
    1.40
    彼は
    1.26
    彼の
    1.24
     His
    1.19
     HIS
    1.19
    Activations Density 0.852%

    No Known Activations