© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103684
    Prev
    Next
    INDEX
    Explanations

    words that suggest a degree of approximation or non-exactness

    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
     also
    -0.35
     and
    -0.32
     this
    -0.30
     ALSO
    -0.28
    also
    -0.27
    this
    -0.25
     later
    -0.25
     συμβ
    -0.25
     cours
    -0.25
     you
    -0.25
    POSITIVE LOGITS
     virtually
    1.02
     Virtually
    0.99
     nearly
    0.98
     practically
    0.96
    AddTagHelper
    0.95
     Practically
    0.95
     almost
    0.94
    ctically
    0.94
    Nearly
    0.94
     Nearly
    0.93
    Activations Density 0.028%

    No Known Activations