© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7145
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.61
    WindowConstants
    -0.57
    SequentialGroup
    -0.55
    koneksi
    -0.55
     Mahomet
    -0.55
     carter
    -0.54
    Skocz
    -0.52
     vnto
    -0.51
     Sangat
    -0.51
    Portály
    -0.50
    POSITIVE LOGITS
     the
    0.77
    hauled
    0.65
     onOptions
    0.65
     endorsing
    0.62
    PerformLayout
    0.61
    __(/*!
    0.61
    oureuse
    0.60
    runApp
    0.60
     pierdas
    0.60
    niz
    0.60
    Activations Density 0.559%

    No Known Activations