© 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. 38-GEMMASCOPE-RES-16K
    11. 15040
    Prev
    Next
    INDEX
    Explanations

    phrases indicating multiple instances or complexities involving parameters and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.60
    UnsafeEnabled
    -0.59
    GOTREF
    -0.53
     '\\;'
    -0.52
    Jeografia
    -0.50
    expandindo
    -0.49
    StoryboardSegue
    -0.49
     Италијани
    -0.48
     &___
    -0.47
     Italijanski
    -0.46
    POSITIVE LOGITS
     multiple
    3.14
    multiple
    2.73
    Multiple
    2.59
     Multiple
    2.56
     MULTIPLE
    2.41
    MULTIPLE
    2.16
     meerdere
    2.13
     múltiples
    2.09
    複数の
    2.03
    複数
    1.93
    Activations Density 1.693%

    No Known Activations