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. 9-GEMMASCOPE-RES-16K
    6. 3356
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "download" and related terms in various contexts

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

    "download"

    np_acts-logits-general · gemini-2.0-flash

    download files and software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fieldNum
    -0.63
     CURIAM
    -0.63
    stateMutability
    -0.58
    quelize
    -0.57
     Sequelize
    -0.56
     StringVar
    -0.55
    iomanip
    -0.54
    modelBuilder
    -0.53
     dezelve
    -0.53
    strix
    -0.52
    POSITIVE LOGITS
     download
    1.99
    Download
    1.81
    download
    1.79
     Download
    1.76
     downloaded
    1.75
     downloading
    1.71
     downloads
    1.70
    下载
    1.52
     DOWNLOAD
    1.51
    DOWNLOAD
    1.47
    Activations Density 0.148%

    No Known Activations