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. 19-GEMMASCOPE-RES-16K
    6. 2133
    Prev
    Next
    INDEX
    Explanations

    sentences expressing feelings and states of being, particularly regarding waking up and experiencing a day

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.67
     CURIAM
    -0.47
    ęku
    -0.47
    (&:
    -0.46
    uku
    -0.46
    HTTPClient
    -0.45
     facie
    -0.45
    LIBRA
    -0.45
    ikaze
    -0.44
     Recht
    -0.44
    POSITIVE LOGITS
     morning
    2.09
     breakfast
    1.96
     waking
    1.82
     Breakfast
    1.77
    morning
    1.76
    Breakfast
    1.75
     wake
    1.74
    Morning
    1.71
     Morning
    1.70
     mornings
    1.70
    Activations Density 0.186%

    No Known Activations