© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 662
    Prev
    Next
    INDEX
    Explanations

    references to people and their needs or actions

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

    "people" or "People"

    np_acts-logits-general · gemini-2.0-flash

    people watcher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    我が家の
    -0.51
    avax
    -0.46
     coroa
    -0.46
     Martel
    -0.44
     taglio
    -0.43
     sinistro
    -0.43
     debut
    -0.41
     initial
    -0.41
     trasparente
    -0.41
     Clovis
    -0.40
    POSITIVE LOGITS
    People
    1.26
    people
    1.23
     People
    1.23
     PEOPLE
    1.20
    PEOPLE
    1.18
     people
    1.15
     ppl
    0.90
    Person
    0.88
     person
    0.88
     Person
    0.86
    Activations Density 0.091%

    No Known Activations