© 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. 0-GEMMASCOPE-RES-16K
    11. 8021
    Prev
    Next
    INDEX
    Explanations

    terms and phrases indicating the concept of being alive or existing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.81
    PerformLayout
    -0.69
    ſelf
    -0.67
    parsedMessage
    -0.65
    AddTagHelper
    -0.65
     NSCoder
    -0.64
     EconPapers
    -0.62
    afficheront
    -0.59
     Houſe
    -0.59
    ImageContext
    -0.58
    POSITIVE LOGITS
     external
    0.66
     internal
    0.61
     anti
    0.52
    external
    0.48
    internal
    0.48
     External
    0.47
     du
    0.46
     sounding
    0.44
    ANTS
    0.43
     INTERNAL
    0.43
    Activations Density 0.266%

    No Known Activations