© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9257
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "I think."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    事に
    -0.47
    ouwen
    -0.46
     sū
    -0.43
    x
    -0.42
     vinyle
    -0.42
     my
    -0.42
     Darlington
    -0.41
    事を
    -0.41
    化
    -0.41
     mely
    -0.41
    POSITIVE LOGITS
    umably
    1.13
     glaube
    1.11
     perhaps
    1.04
    Probably
    1.02
    おそらく
    1.02
    mutlich
    1.02
     probably
    1.01
     probablemente
    1.00
    probably
    1.00
     Probably
    0.99
    Activations Density 0.208%

    No Known Activations