© 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. 102423
    Prev
    Next
    INDEX
    Explanations

    phrases expressing need or obligation

    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
    racene
    -0.46
    новништво
    -0.45
    enterOuterAlt
    -0.45
     murni
    -0.41
    割と
    -0.40
    Ӕ
    -0.40
    mitos
    -0.40
     kdy
    -0.39
     betrug
    -0.39
     manufactured
    -0.39
    POSITIVE LOGITS
     gotta
    0.66
     must
    0.65
     måste
    0.62
    must
    0.62
     Gotta
    0.60
     MUST
    0.58
    Must
    0.58
    MUST
    0.58
     Must
    0.58
    Gotta
    0.57
    Activations Density 0.027%

    No Known Activations