© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 98885
    Prev
    Next
    INDEX
    Explanations

    phrases related to monitoring and evaluation processes

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

    survey data, control systems

    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
    rungsseite
    -0.69
     ujednoznacz
    -0.58
     مشين
    -0.56
    CppMethod
    -0.56
    ChildScrollView
    -0.54
     للاسماء
    -0.51
    ifikationer
    -0.51
     متعلقه
    -0.49
    WriteAttribute
    -0.48
    alva
    -0.47
    POSITIVE LOGITS
     feedback
    0.52
     monitoring
    0.48
    anniversaire
    0.43
     performance
    0.42
    Monitoring
    0.41
     Monitoring
    0.41
    MessageTagHelper
    0.40
     mendengarkan
    0.40
     success
    0.39
     Erfolge
    0.39
    Activations Density 0.038%

    No Known Activations