© 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. 5647
    Prev
    Next
    INDEX
    Explanations

    details related to the description of physical spaces and environments

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

    Rooms in a house

    np_acts-logits-general · gemini-2.0-flash

    rooms in a house

    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
     الحره
    -0.55
     محفوظة
    -0.53
    存于互联网档案馆
    -0.51
    retty
    -0.51
     InputDecoration
    -0.49
     bagay
    -0.47
    atação
    -0.47
    Vidite
    -0.46
    /*:
    -0.46
     aug
    -0.46
    POSITIVE LOGITS
     living
    1.71
    living
    1.48
     Living
    1.42
    Living
    1.37
     kitchen
    1.31
     dining
    1.31
     LIVING
    1.25
     bedroom
    1.19
    LIVING
    1.14
     Dining
    1.09
    Activations Density 0.131%

    No Known Activations