© 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
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15484
    Prev
    Next
    INDEX
    Explanations

    references to people and their actions or attributes in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mekan
    -0.43
     requerimientos
    -0.34
     mécanique
    -0.34
     imponer
    -0.31
     rechazar
    -0.30
     fotográfica
    -0.30
     McKin
    -0.30
     conserver
    -0.29
     공
    -0.29
     wyma
    -0.29
    POSITIVE LOGITS
     people
    1.23
    people
    1.08
     People
    1.03
     PEOPLE
    1.02
    People
    1.01
     ppl
    1.00
     peoples
    0.97
     persons
    0.94
     människor
    0.93
    PEOPLE
    0.90
    Activations Density 0.551%

    No Known Activations