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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6364
    Prev
    Next
    INDEX
    Explanations

    phrases related to tracking and searching for people or objects

    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
    XmlAccessType
    -0.39
    Flip
    -0.35
     otomatig
    -0.33
    Examine
    -0.33
    Future
    -0.33
    Pop
    -0.33
    fjspx
    -0.33
    tempt
    -0.32
    AccessorTable
    -0.32
     javafx
    -0.31
    POSITIVE LOGITS
     찾
    0.79
     search
    0.78
     locating
    0.77
     searched
    0.73
     whereabouts
    0.71
     searches
    0.71
     finder
    0.70
     locate
    0.69
     Search
    0.68
    찾
    0.68
    Activations Density 0.395%

    No Known Activations