© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101970
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or strong assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     után
    -0.32
    ,
    -0.31
     and
    -0.31
    ;
    -0.30
     therefore
    -0.29
     This
    -0.28
     this
    -0.27
    がか
    -0.27
     vergangenen
    -0.26
     Auflage
    -0.26
    POSITIVE LOGITS
     kasarigan
    1.07
    rungsseite
    0.96
     utafitiHapana
    0.87
    OGND
    0.83
    <unused8>
    0.78
     noDo
    0.78
    <unused79>
    0.78
    <unused43>
    0.78
    <unused41>
    0.78
    <unused17>
    0.77
    Activations Density 0.039%

    No Known Activations