© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8337
    Prev
    Next
    INDEX
    Explanations

    phrases related to support services and community events

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

    Days of the week and recurring events

    np_acts-logits-general · gemini-2.0-flash

    weekly, monthly, quarterly events

    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
    prnewswire
    -0.68
    
    -0.63
    PRWEB
    -0.59
    IUrlHelper
    -0.58
     Delegates
    -0.56
    defer
    -0.54
    VYMaps
    -0.53
    帖最后由
    -0.53
     Delegate
    -0.53
    Festival
    -0.52
    POSITIVE LOGITS
     Tuesdays
    1.37
     Wednesdays
    1.34
     Mondays
    1.27
     Thursdays
    1.24
     monthly
    1.20
     weekly
    1.19
     meetings
    1.07
    Tues
    1.03
     meets
    1.01
    ednesdays
    0.99
    Activations Density 0.172%

    No Known Activations