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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11010
    Prev
    Next
    INDEX
    Explanations

    references to social invitations and gatherings

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

    parties or gatherings

    np_acts-logits-general · gemini-2.0-flash

    party guests invitations

    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
     liné
    -0.54
    pernicus
    -0.53
    ExecuteNonQuery
    -0.53
    (!__
    -0.53
    сылкі
    -0.51
    Personensuche
    -0.50
     harian
    -0.49
    ulemon
    -0.48
     réfé
    -0.48
    typeorm
    -0.47
    POSITIVE LOGITS
     guests
    1.73
     party
    1.70
     invite
    1.48
    party
    1.47
     PARTY
    1.46
     Party
    1.43
     Guests
    1.43
     invitations
    1.43
     guest
    1.40
    Guests
    1.40
    Activations Density 0.246%

    No Known Activations