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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9892
    Prev
    Next
    INDEX
    Explanations

    kinship and family relationships, particularly names and connections among family members

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

    Names that could be first names

    np_acts-logits-general · gemini-2.0-flash

    names of brothers and individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Amanda
    -0.84
     Sarah
    -0.82
     Maria
    -0.80
     Rebecca
    -0.80
     Michelle
    -0.80
     Melissa
    -0.79
    Sarah
    -0.78
    Amanda
    -0.77
    Michelle
    -0.77
     Emily
    -0.76
    POSITIVE LOGITS
    tagHelperRunner
    0.64
     Clarence
    0.62
     Harry
    0.59
     Harold
    0.56
     Clyde
    0.54
    Clarence
    0.53
     Ralph
    0.53
    CloseOperation
    0.53
     Clifford
    0.53
     Alvin
    0.52
    Activations Density 0.329%

    No Known Activations