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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8038
    Prev
    Next
    INDEX
    Explanations

    references to organizations or acronyms beginning with "Am" and variations of that prefix

    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
    :✨
    -0.44
     dele
    -0.39
    findpost
    -0.38
    SerializedName
    -0.38
     CURIAM
    -0.37
     Paglinawan
    -0.36
     VizieR
    -0.35
    Région
    -0.35
    ListActivity
    -0.35
    🔙
    -0.35
    POSITIVE LOGITS
     Am
    0.66
    Am
    0.57
     am
    0.54
    StoryboardSegue
    0.46
    Amicalement
    0.45
     ostavi
    0.44
    Sucesor
    0.44
    دانشنامهٔ
    0.44
    parametrize
    0.43
    ClInclude
    0.41
    Activations Density 0.234%

    No Known Activations