© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10055
    Prev
    Next
    INDEX
    Explanations

    phrases related to community engagement and support

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

    "Community" followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    community: centers, research, service, tension

    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
    LookAnd
    -0.80
    ResumeLayout
    -0.78
    
    -0.78
     AssemblyCulture
    -0.78
     @"/
    -0.76
    bootstrapcdn
    -0.75
    μως
    -0.75
    WriteTagHelper
    -0.74
    httphttps
    -0.73
    plotlib
    -0.73
    POSITIVE LOGITS
     members
    0.69
    wide
    0.64
     spirit
    0.61
     relations
    0.57
     membres
    0.56
     college
    0.56
     member
    0.55
     engagement
    0.54
    livejournal
    0.53
     service
    0.52
    Activations Density 0.044%

    No Known Activations