© 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. 1-GEMMASCOPE-RES-16K
    6. 10623
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "taught."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageField
    -0.60
    aited
    -0.56
     Rejo
    -0.53
     boogie
    -0.52
    ängen
    -0.51
     olun
    -0.51
    DebuggerStep
    -0.50
     ganglion
    -0.46
    kra
    -0.46
    วง
    -0.46
    POSITIVE LOGITS
     taught
    1.46
    taught
    1.24
     Taught
    1.20
    awtextra
    0.86
     teach
    0.83
     teaches
    0.78
     typelib
    0.77
     estekak
    0.73
     ErrInvalid
    0.70
    ⓧ
    0.69
    Activations Density 0.057%

    No Known Activations