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. 24-GEMMASCOPE-RES-131K
    6. 849
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions related to computer science and mathematics

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

    special cases and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.62
     &___
    -0.56
    DECREF
    -0.53
    Tikang
    -0.50
     NSCoder
    -0.49
     interesa
    -0.48
    warnai
    -0.47
     interesan
    -0.47
    xnn
    -0.47
    Географиясе
    -0.45
    POSITIVE LOGITS
    readystatechange
    0.40
    Tracce
    0.36
    invokeLater
    0.33
    ActionCreators
    0.33
    olta
    0.32
    MetaObject
    0.31
     simpler
    0.31
     readily
    0.31
     sooner
    0.30
    contentLoaded
    0.30
    Activations Density 0.221%

    No Known Activations