© 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. 10254
    Prev
    Next
    INDEX
    Explanations

    references to "new" items or concepts

    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
     Winaray
    -0.56
     propOrder
    -0.54
    UrlResolution
    -0.53
    operatorname
    -0.52
    ISME
    -0.51
    RemindMe
    -0.49
     courseId
    -0.49
    ceptre
    -0.48
     Lombardi
    -0.47
     onFailure
    -0.47
    POSITIVE LOGITS
     new
    1.28
    new
    1.17
     New
    1.11
     NEW
    1.09
    New
    1.06
    NEW
    0.98
     Nuevas
    0.94
     neuen
    0.91
     nueva
    0.89
     nieuwe
    0.88
    Activations Density 0.111%

    No Known Activations