© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 15953
    Prev
    Next
    INDEX
    Explanations

    phrases related to invitations and inviting people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stroud
    -0.61
    Personensuche
    -0.60
    談社
    -0.60
     '\\;'
    -0.58
     meurt
    -0.57
    RepeatedField
    -0.57
    ValueGeneration
    -0.57
    Rhestr
    -0.57
     IService
    -0.57
    lismo
    -0.57
    POSITIVE LOGITS
     invite
    3.20
     invitation
    3.13
     invites
    2.97
     invited
    2.89
     invitations
    2.88
     Invite
    2.86
    invite
    2.67
    Invite
    2.64
     inviting
    2.64
     Invitation
    2.54
    Activations Density 0.059%

    No Known Activations