© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 6495
    Prev
    Next
    INDEX
    Explanations

    mentions of disks or discs in various contexts related to storage or data retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WindowConstants
    -0.39
     moletom
    -0.38
     zawod
    -0.35
     įsi
    -0.35
     asmen
    -0.34
     forthcoming
    -0.34
     fallecido
    -0.34
    iausi
    -0.34
     cálido
    -0.34
     helicóptero
    -0.34
    POSITIVE LOGITS
     disk
    1.03
    disk
    0.97
     Disk
    0.94
     disc
    0.88
     fiber
    0.83
     mod
    0.81
     fibre
    0.80
     Fiber
    0.80
    Disk
    0.78
     Retrieval
    0.77
    Activations Density 0.122%

    No Known Activations