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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12752
    Prev
    Next
    INDEX
    Explanations

    terms related to mobile app development and associated services

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

    App development, slots, mold, and product manufacturers

    np_acts-logits-general · gemini-2.0-flash

    companies or services

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     betweenstory
    -0.74
     nakalista
    -0.59
     jScrollPane
    -0.57
    Referințe
    -0.56
     مشين
    -0.56
     kasarigan
    -0.56
    Aiheesta
    -0.52
    IVEREF
    -0.51
     CURIAM
    -0.49
    sizeCache
    -0.48
    POSITIVE LOGITS
    FactoryBean
    0.36
    Advantages
    0.32
     Advantages
    0.32
    kheim
    0.32
    Hard
    0.31
    Healthcare
    0.30
    chappen
    0.30
     ГОСТ
    0.30
     vantagens
    0.30
     Hard
    0.30
    Activations Density 0.471%

    No Known Activations