© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15276
    Prev
    Next
    INDEX
    Explanations

    occurrences of words and phrases with the prefix "th" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     سكانية
    -0.68
    parsedMessage
    -0.64
    >`;
    -0.61
    +#+
    -0.58
    VersionUID
    -0.57
    principalColumn
    -0.57
    !*\
    -0.57
    Rüyada
    -0.57
    .)}
    -0.56
     opi
    -0.56
    POSITIVE LOGITS
    th
    0.83
    TH
    0.75
    Th
    0.66
     Th
    0.64
     Thi
    0.62
    uth
    0.60
    thom
    0.58
    UTH
    0.58
    Thunk
    0.57
     transición
    0.56
    Activations Density 0.290%

    No Known Activations