© 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. 16-GEMMASCOPE-RES-16K
    11. 14712
    Prev
    Next
    INDEX
    Explanations

    key terms related to sports and their analysis

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

    Word before "was," "did," or "league."

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs

    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
    currently
    -0.86
     currently
    -0.86
     Currently
    -0.80
     đang
    -0.80
    Currently
    -0.78
     presently
    -0.78
     CURRENT
    -0.73
     attualmente
    -0.72
     current
    -0.70
     atualmente
    -0.69
    POSITIVE LOGITS
     did
    0.89
     estuvo
    0.88
     was
    0.83
     estuvieron
    0.82
     ended
    0.80
     worked
    0.74
     helped
    0.71
     didn
    0.71
    did
    0.71
     didnt
    0.71
    Activations Density 0.741%

    No Known Activations