© 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. 22-GEMMASCOPE-RES-16K
    11. 12686
    Prev
    Next
    INDEX
    Explanations

    content related to travel experiences and holiday planning

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

    following "a," "your," or describing a vacation

    np_acts-logits-general · gemini-2.0-flash

    hotel stay

    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
     commuters
    -0.53
     cafe
    -0.53
    Commons
    -0.52
    uss
    -0.52
     malls
    -0.52
     SIMBAD
    -0.51
     cafes
    -0.51
     HOUR
    -0.51
     Cafe
    -0.50
    Cafe
    -0.50
    POSITIVE LOGITS
     stay
    1.16
    stay
    1.01
     Stay
    0.92
     stays
    0.89
    Stay
    0.88
    STAY
    0.84
     stayed
    0.81
     STAY
    0.81
    stays
    0.80
     staying
    0.78
    Activations Density 0.095%

    No Known Activations