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

    Neuronpedia

    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. 2-GEMMASCOPE-RES-16K
    11. 4579
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "familiar."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.57
     المعيارى
    -0.54
     basics
    -0.50
    pantalones
    -0.50
     skolan
    -0.49
    Билгалдахарш
    -0.49
    ußt
    -0.47
     Consejos
    -0.47
     templado
    -0.47
    acimiento
    -0.46
    POSITIVE LOGITS
     familiar
    3.05
    familiar
    2.67
     Familiar
    2.56
    Familiar
    2.47
     familiarity
    1.97
    熟悉
    1.65
    熟悉的
    1.63
     famili
    1.61
     familiarize
    1.60
    famili
    1.48
    Activations Density 0.097%

    No Known Activations