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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 125866
    Prev
    Next
    INDEX
    Explanations

    references to episodes and seasons of television shows

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

    Episode/program, comment, check in

    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
     avoient
    -0.44
     isNameExpr
    -0.41
    isNameExpr
    -0.41
     arbete
    -0.40
     ägg
    -0.39
    ställning
    -0.39
     capuz
    -0.39
     ORA
    -0.38
    Messenger
    -0.38
     BrowserRouter
    -0.38
    POSITIVE LOGITS
    一道
    0.60
    这张
    0.59
    MigrationBuilder
    0.55
    webElementXpaths
    0.53
    这场
    0.52
    这篇
    0.52
    这部
    0.50
    一家
    0.50
    一颗
    0.50
    这座
    0.49
    Activations Density 0.004%

    No Known Activations