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. 108295
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms and their impact on market metrics

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

    social media platforms and internet companies

    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
     Infórmanos
    -0.45
    +#+#
    -0.43
     Manns
    -0.42
    vins
    -0.41
    argin
    -0.41
     Magazin
    -0.40
    -------------</
    -0.40
     sympathize
    -0.40
    entum
    -0.40
    ents
    -0.39
    POSITIVE LOGITS
    centralwidget
    0.57
    twimg
    0.55
    StackNavigator
    0.48
    mobileqq
    0.47
     argint
    0.47
     Facebook
    0.46
     Instagram
    0.45
     platform
    0.42
     Twitter
    0.41
     ägg
    0.41
    Activations Density 0.029%

    No Known Activations