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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 10067
    Prev
    Next
    INDEX
    Explanations

    terms related to disk and storage management

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

    Computer storage: disk, memory, space

    np_acts-logits-general · gemini-2.0-flash

    disk space and memory

    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
    criptive
    -0.55
    DotNetBar
    -0.53
    Referanser
    -0.53
    rungsseite
    -0.52
    parsedMessage
    -0.49
    endente
    -0.49
    InjectAttribute
    -0.48
    jectable
    -0.48
    enablog
    -0.48
    Искәрмәләр
    -0.48
    POSITIVE LOGITS
     disk
    0.87
     storage
    0.86
    storage
    0.82
    Disk
    0.80
    disk
    0.79
     memory
    0.75
     Storage
    0.74
    Storage
    0.73
     Disk
    0.71
     Memory
    0.69
    Activations Density 0.407%

    No Known Activations