© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12147
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups indicated by the word "who."

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

    "Who" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    who followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lt
    -0.52
    t
    -0.45
     EST
    -0.45
    mdash
    -0.45
    left
    -0.43
     Sanford
    -0.43
    get
    -0.42
    8
    -0.42
    ess
    -0.42
    ton
    -0.41
    POSITIVE LOGITS
    rungsseite
    1.03
     queſta
    1.02
     którzy
    0.91
     kteří
    0.90
    LookAnd
    0.83
    SequentialGroup
    0.82
     Numerade
    0.82
     who
    0.81
    MessageOf
    0.80
     ktorí
    0.79
    Activations Density 0.105%

    No Known Activations