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. 56740
    Prev
    Next
    INDEX
    Explanations

    statements and phrases related to the launch and features of new software applications

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

    first person plural pronouns

    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
    GEBURTSDATUM
    -0.69
     snippetHide
    -0.66
     transférez
    -0.65
    AndEndTag
    -0.63
    PropertyChanging
    -0.60
     linkovi
    -0.57
    Билгалдахарш
    -0.55
    цездатний
    -0.54
    ніципалі
    -0.53
    ագրություններ
    -0.52
    POSITIVE LOGITS
     our
    0.50
     we
    0.50
     ourselves
    0.46
    We
    0.41
    是我们
    0.40
    我们将
    0.40
    Tenemos
    0.39
    我们
    0.38
    我们需要
    0.38
    Delicious
    0.37
    Activations Density 0.032%

    No Known Activations