Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3449
    Prev
    Next
    INDEX
    Explanations

    phrases related to downloads, specifically focusing on torrents and free software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SharedDtor
    -0.54
    Bibliografie
    -0.49
    Cyfarwyddwr
    -0.48
    GenerationType
    -0.46
    parsedMessage
    -0.44
    ensus
    -0.42
     ReactDOM
    -0.42
    Sklici
    -0.40
    #!/
    -0.40
    URLException
    -0.40
    POSITIVE LOGITS
    Torrent
    0.53
    torrent
    0.47
     torrents
    0.45
    twimg
    0.45
     torrent
    0.45
     illegal
    0.44
     Torrent
    0.42
    illegal
    0.42
     pirated
    0.41
    multer
    0.41
    Activations Density 0.492%

    No Known Activations