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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68942
    Prev
    Next
    INDEX
    Explanations

    terms related to programming interfaces and their definitions

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

    software interface definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.56
    initComponents
    -0.54
    脚注の使い方
    -0.53
     anggaran
    -0.51
     Bioaccumulative
    -0.50
    webElementXpaths
    -0.49
    зулта
    -0.49
     useHistory
    -0.47
    tagHelperRunner
    -0.47
     Infór
    -0.45
    POSITIVE LOGITS
    abstractmethod
    0.49
    demand
    0.47
     demands
    0.47
     requirements
    0.44
     Demand
    0.44
     demand
    0.42
     требования
    0.42
     Demands
    0.42
    要求
    0.42
    INTERFACE
    0.40
    Activations Density 0.042%

    No Known Activations