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. 38857
    Prev
    Next
    INDEX
    Explanations

    references to media literacy and the understanding of fake news among children and students

    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
    AndEndTag
    -0.54
    ագրություններ
    -0.48
    ésultat
    -0.48
    BeginContext
    -0.45
     propOrder
    -0.45
     productividad
    -0.45
    ကိုးကား
    -0.42
    ContentAsync
    -0.41
    !*\
    -0.41
    ceral
    -0.40
    POSITIVE LOGITS
    Resist
    0.50
     Resist
    0.49
     resist
    0.47
     Resistant
    0.44
     vững
    0.44
     withstand
    0.42
     resisting
    0.41
    hadur
    0.40
     RESIST
    0.40
     resistir
    0.40
    Activations Density 0.107%

    No Known Activations