© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11368
    Prev
    Next
    INDEX
    Explanations

    terms associated with hosting and guest management during events

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

    "Guest" and related terms

    np_acts-logits-general · gemini-2.0-flash

    guest, guests, visitors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.52
    كويكب
    -0.51
    fromnode
    -0.48
    PreExecute
    -0.48
     sasa
    -0.46
    ///<
    -0.44
    mapStateToProps
    -0.44
    pendente
    -0.43
     suaminya
    -0.43
    bolista
    -0.42
    POSITIVE LOGITS
     guest
    2.71
     guests
    2.69
    guest
    2.41
     Guest
    2.36
     Guests
    2.34
     GUEST
    2.34
    Guest
    2.32
    Guests
    2.23
    guests
    2.23
    GUEST
    2.15
    Activations Density 0.155%

    No Known Activations