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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15110
    Prev
    Next
    INDEX
    Explanations

    elements related to food, packaging, and maintenance tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
     Numerade
    -0.69
    InjectAttribute
    -0.68
    ftagPool
    -0.66
    webElementXpaths
    -0.64
    richTextPanel
    -0.61
     mergeFrom
    -0.60
     COMMERCIAL
    -0.59
     WaitForSeconds
    -0.58
     sumpay
    -0.58
     uLocal
    -0.58
    POSITIVE LOGITS
     themselves
    0.38
     itself
    0.31
     utafitiHapana
    0.28
    Tikang
    0.27
     herself
    0.27
     fees
    0.27
     stesse
    0.27
    <bos>
    0.26
    StringCopy
    0.26
     fee
    0.25
    Activations Density 0.601%

    No Known Activations