Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11143
    Prev
    Next
    INDEX
    Explanations

    references to medical treatment responsibilities and patient care

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

    Followed by "regardless"

    np_acts-logits-general · gemini-2.0-flash

    whether or regardless

    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
     OFDb
    -0.64
    Autoritní
    -0.57
     (?,
    -0.52
     JAXBElement
    -0.52
     típica
    -0.49
     Normdatei
    -0.49
     Obrador
    -0.49
     stb
    -0.48
    ContentAsync
    -0.48
     típicos
    -0.47
    POSITIVE LOGITS
     whether
    3.17
     regardless
    2.87
    whether
    2.85
    regardless
    2.63
     Whether
    2.62
    Whether
    2.54
     WHETHER
    2.51
     irrespective
    2.48
     Regardless
    2.32
    Regardless
    2.30
    Activations Density 0.791%

    No Known Activations