© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119862
    Prev
    Next
    INDEX
    Explanations

    repetitive use of the word "and" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     chaus
    -0.36
     rather
    -0.35
    ┘
    -0.32
     boî
    -0.32
    一代
    -0.32
    .
    -0.31
     the
    -0.31
    GTCX
    -0.30
     via
    -0.30
     my
    -0.30
    POSITIVE LOGITS
     Anſ
    0.60
     betweenstory
    0.59
     ſind
    0.56
     typelib
    0.54
     Carthage
    0.54
     purpoſe
    0.54
     Beſ
    0.53
     ſame
    0.52
    mpagne
    0.52
    ロウィン
    0.52
    Activations Density 0.052%

    No Known Activations