© 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. 124936
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to data compression and quantization techniques

    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
    stateMutability
    -0.37
    úrese
    -0.34
     prayer
    -0.31
     konsek
    -0.31
     active
    -0.30
    active
    -0.30
    nezeu
    -0.30
    पया
    -0.30
    жалуйста
    -0.29
    impinan
    -0.29
    POSITIVE LOGITS
    ]")]
    0.57
    AccessFile
    0.57
     estekak
    0.55
    TagHelper
    0.55
    rungsseite
    0.54
    Билгалдахарш
    0.54
    GHIJKLM
    0.53
    Tracce
    0.53
    tershire
    0.52
     wireType
    0.52
    Activations Density 0.160%

    No Known Activations