© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 15153
    Prev
    Next
    INDEX
    Explanations

    terms related to individuals or groups of individuals

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

    "person" or "persons"

    np_acts-logits-general · gemini-2.0-flash

    person-to-person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.91
    hysema
    -0.85
    PerformLayout
    -0.85
    warded
    -0.81
     purging
    -0.80
     Idy
    -0.79
    extAlignment
    -0.79
    Datuak
    -0.79
     Navarre
    -0.78
     Kie
    -0.78
    POSITIVE LOGITS
     Persons
    1.39
     Person
    1.36
     PERSON
    1.29
    Persons
    1.29
     persons
    1.23
     person
    1.23
    persons
    1.21
     PERSONS
    1.20
    person
    1.20
    Person
    1.18
    Activations Density 0.024%

    No Known Activations