© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 2892
    Prev
    Next
    INDEX
    Explanations

    instances of the word "those" and its variations, indicating a focus on specific groups or people

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

    "Those" followed by relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    those who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentLoaded
    -0.39
    initro
    -0.37
    PRWEB
    -0.35
    ftc
    -0.34
    tadır
    -0.34
    kháu
    -0.34
    namt
    -0.33
    quiel
    -0.33
     FileReader
    -0.33
     referrerpolicy
    -0.33
    POSITIVE LOGITS
     who
    0.84
    jenigen
    0.68
     ProtoMessage
    0.56
     którzy
    0.56
     betrokken
    0.56
     jotka
    0.53
    zelfde
    0.53
     hvem
    0.52
     whom
    0.51
    jenige
    0.50
    Activations Density 0.110%

    No Known Activations