© 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. 37-GEMMASCOPE-RES-16K
    11. 3939
    Prev
    Next
    INDEX
    Explanations

    references to software components and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     E
    -1.36
    E
    -1.23
     e
    -1.14
    e
    -0.86
    getE
    -0.80
    Ｅ
    -0.66
     ई
    -0.65
    ᴇ
    -0.51
    ｅ
    -0.51
    New
    -0.49
    POSITIVE LOGITS
    InSection
    0.52
    UIControlState
    0.51
     Эр
    0.49
     betweenstory
    0.47
    ModelSerializer
    0.47
    contentLoaded
    0.47
    tagHelperRunner
    0.47
     onAnimation
    0.47
     Parcelable
    0.47
    openzeppelin
    0.47
    Activations Density 1.543%

    No Known Activations