© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 4674
    Prev
    Next
    INDEX
    Explanations

    references to editing, composition, and technical processes related to media and content creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sewing machines or editing tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PositiveButton
    -0.56
     AssemblyCompany
    -0.52
     nim
    -0.50
    ymce
    -0.49
    AutoField
    -0.47
    FirstResponder
    -0.46
    AlterField
    -0.45
    tims
    -0.45
    BagLayout
    -0.45
     AssemblyTitle
    -0.44
    POSITIVE LOGITS
     springfox
    0.40
     verrez
    0.38
     dianteiro
    0.38
     artificiales
    0.37
     funcionales
    0.36
     quæ
    0.36
     colgantes
    0.36
     inalámbrico
    0.36
     EconPapers
    0.36
     ainfi
    0.35
    Activations Density 0.099%

    No Known Activations