© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27801
    Prev
    Next
    INDEX
    Explanations

    references to timing and reporting in the context of events

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

    on days or months

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     itſelf
    -0.91
     Reſ
    -0.88
     Theſe
    -0.88
     unſ
    -0.83
     faſt
    -0.75
     Monfieur
    -0.75
     raiſ
    -0.73
     ་་
    -0.73
     Houſe
    -0.72
     greateſt
    -0.72
    POSITIVE LOGITS
     Tuesday
    0.53
     Friday
    0.52
     Saturday
    0.50
     Thursday
    0.48
     Wednesday
    0.48
    path
    0.47
    ap
    0.46
    okovic
    0.46
     Monday
    0.44
     today
    0.44
    Activations Density 0.017%

    No Known Activations