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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114651
    Prev
    Next
    INDEX
    Explanations

    programming concepts and terminology related to software development and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Conclusão
    -0.37
     Photocase
    -0.36
    issory
    -0.34
    TestBase
    -0.34
     favoring
    -0.34
     pasti
    -0.34
    Sun
    -0.33
    Criteria
    -0.33
     CONCLUSIONS
    -0.32
    Save
    -0.32
    POSITIVE LOGITS
     WaitForSeconds
    0.44
     automatic
    0.43
    Controllo
    0.43
     автомати
    0.43
     automated
    0.43
    tomation
    0.43
     ThemeData
    0.43
    AddTagHelper
    0.42
    insic
    0.42
     register
    0.42
    Activations Density 0.222%

    No Known Activations