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. 974
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

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

    URLs and domain names

    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
    EndProject
    -0.38
    tees
    -0.36
    だが
    -0.36
    الحياه
    -0.36
    sur
    -0.35
     ſur
    -0.35
     Mili
    -0.35
     ото
    -0.34
    NTS
    -0.34
     succeeding
    -0.33
    POSITIVE LOGITS
     المعيارى
    0.59
    parsedMessage
    0.57
    ContentAsync
    0.51
    AsUp
    0.50
     betweenstory
    0.50
     Wicidata
    0.46
     doInBackground
    0.46
     Paglinawan
    0.46
    Джерела
    0.46
     gynhyrchwyd
    0.45
    Activations Density 0.017%

    No Known Activations