© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1849
    Prev
    Next
    INDEX
    Explanations

    mentions of 'person' and variations of it, indicating a focus on individuals and their characteristics

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

    The token "person" or "persons"

    np_acts-logits-general · gemini-2.0-flash

    person or persons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     wireType
    -0.67
    Fordítás
    -0.56
    ⓧ
    -0.55
    libatkan
    -0.50
    ContentLoaded
    -0.47
     setLoading
    -0.47
    INFL
    -0.46
    convite
    -0.46
     waffle
    -0.46
     camuf
    -0.46
    POSITIVE LOGITS
    Person
    0.93
     Person
    0.91
     person
    0.90
    person
    0.86
    persons
    0.82
    PERSON
    0.80
     persons
    0.80
    Persons
    0.79
     Persons
    0.78
     PERSON
    0.78
    Activations Density 0.095%

    No Known Activations