Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 517
    Prev
    Next
    INDEX
    Explanations

    mentions of groups or organizations involving the word "people."

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

    "People" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    People v

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.90
    AnchorStyles
    -0.90
    argout
    -0.83
    AddTagHelper
    -0.82
     IBOutlet
    -0.78
    istoitu
    -0.75
    ConstraintMaker
    -0.75
    ็จ
    -0.74
    OGND
    -0.73
    Népesség
    -0.73
    POSITIVE LOGITS
     People
    0.93
     who
    0.93
    People
    0.92
     PEOPLE
    0.92
     people
    0.90
    people
    0.86
    PEOPLE
    0.85
    tvguidetime
    0.66
     comune
    0.57
     Люди
    0.56
    Activations Density 0.093%

    No Known Activations