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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13038
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data storage and file systems

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

    hard drives and disks

    np_acts-logits-general · gemini-2.0-flash

    storage drive capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.54
     malt
    -0.53
    ymce
    -0.52
     ger
    -0.49
     relâche
    -0.48
    íma
    -0.47
     snipers
    -0.47
     Middleton
    -0.47
     Kaffe
    -0.46
    UniformLocation
    -0.46
    POSITIVE LOGITS
     drive
    1.19
     drives
    1.06
     Drive
    1.03
    drive
    0.99
     disk
    0.98
    Drive
    0.95
     Drives
    0.94
     disks
    0.91
     DRIVE
    0.90
     Disk
    0.87
    Activations Density 0.513%

    No Known Activations