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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8687
    Prev
    Next
    INDEX
    Explanations

    programming elements related to model performance metrics and output logging

    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
     informée
    -0.65
    出版年
    -0.57
    slee
    -0.50
    stination
    -0.48
     Sleeper
    -0.47
    TagMode
    -0.47
    NTP
    -0.47
    ScopeManager
    -0.47
     Roskov
    -0.46
    motic
    -0.46
    POSITIVE LOGITS
     results
    0.60
    RegressionTest
    0.50
    results
    0.47
     Durchsch
    0.46
     comparisons
    0.44
     average
    0.44
     comparison
    0.43
     výsled
    0.43
     obtained
    0.42
     Comparing
    0.41
    Activations Density 0.188%

    No Known Activations