Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16198
    Prev
    Next
    INDEX
    Explanations

    structured data or sections in a report or document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سكانية
    -0.61
     nakalista
    -0.56
    PreferredItem
    -0.54
     propOrder
    -0.53
     Monfieur
    -0.52
     Infór
    -0.51
     متعلقه
    -0.51
     CURIAM
    -0.50
     autorytatywna
    -0.49
    Хьажоргаш
    -0.49
    POSITIVE LOGITS
     trick
    0.45
     f
    0.40
     recon
    0.38
     undis
    0.37
     Fri
    0.36
    と思ったら
    0.36
     за
    0.36
     fri
    0.35
    致
    0.35
    ConstraintMaker
    0.35
    Activations Density 0.786%

    No Known Activations