© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 7935
    Prev
    Next
    INDEX
    Explanations

    instances of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leſs
    -0.60
     Landschaft
    -0.48
     Judea
    -0.47
    nate
    -0.47
    odyear
    -0.46
    anera
    -0.46
    elry
    -0.44
     Tibetan
    -0.44
    jutant
    -0.44
    GND
    -0.44
    POSITIVE LOGITS
     WHICH
    1.18
     Which
    1.14
     which
    1.06
    which
    1.05
    Which
    1.04
     wich
    0.81
     والتي
    0.80
    hich
    0.79
     которая
    0.75
     Wich
    0.71
    Activations Density 0.189%

    No Known Activations