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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120750
    Prev
    Next
    INDEX
    Explanations

    elements of user experiences and their understanding of content in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    layoutControl
    -0.35
    iets
    -0.31
    ThemeOverlay
    -0.30
    AddTagHelper
    -0.29
     vimos
    -0.28
    InstrumentedTest
    -0.28
    ToOne
    -0.27
     constate
    -0.26
    Siehe
    -0.26
     tvá
    -0.26
    POSITIVE LOGITS
     للمعارف
    0.60
    :✨
    0.60
    Попис
    0.57
    oredCriteria
    0.56
    期刊论文
    0.56
     complexity
    0.56
     Chwiliwch
    0.52
    $_['
    0.51
    __*/
    0.50
    anair
    0.50
    Activations Density 0.136%

    No Known Activations