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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10768
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaborative opportunities and user invitations

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

    "Join" or "joining" variations

    np_acts-logits-general · gemini-2.0-flash

    joining or becoming part of groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المناصب
    -0.59
    esModule
    -0.52
    zzling
    -0.50
    disposing
    -0.49
    Билгалдахарш
    -0.49
     فريبيس
    -0.49
    itaire
    -0.47
    thaus
    -0.45
    ?>">
    -0.44
    entile
    -0.44
    POSITIVE LOGITS
     joining
    3.21
     join
    3.19
     joins
    2.79
     Joining
    2.79
     joined
    2.77
    join
    2.74
    Joining
    2.73
     Join
    2.64
    Join
    2.58
     JOIN
    2.55
    Activations Density 0.293%

    No Known Activations