© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7631
    Prev
    Next
    INDEX
    Explanations

    descriptions related to competitive sports and athletes

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

    Sentences starting with "I" or expressing observation

    np_acts-logits-general · gemini-2.0-flash

    watching and seeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    towym
    -0.57
     typelib
    -0.57
    AccessorTable
    -0.55
    hdessä
    -0.53
    hü
    -0.53
     Dickerson
    -0.53
     njia
    -0.52
    izacji
    -0.52
    caccio
    -0.49
    ammans
    -0.49
    POSITIVE LOGITS
     my
    0.82
    Watching
    0.81
     मुझे
    0.79
     meines
    0.77
     Watching
    0.76
     watching
    0.74
     veo
    0.73
     Watched
    0.73
     witnessing
    0.72
    watching
    0.71
    Activations Density 0.317%

    No Known Activations