© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3562
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to invitations and the concept of being invited

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.43
     EventEmitter
    -0.40
    makeatother
    -0.40
    JsonKey
    -0.40
    ांकि
    -0.39
    ことができました
    -0.38
     insuff
    -0.37
    InputTagHelper
    -0.36
    ThroughAttribute
    -0.36
    IntOverflow
    -0.35
    POSITIVE LOGITS
    invited
    0.62
    Cure
    0.59
     disambiguazione
    0.57
     Cure
    0.55
     krwi
    0.54
    crime
    0.54
     риск
    0.53
    crimes
    0.53
     PeEnEo
    0.53
    Risk
    0.53
    Activations Density 0.158%

    No Known Activations