© 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. 22-GEMMASCOPE-RES-16K
    6. 8171
    Prev
    Next
    INDEX
    Explanations

    phrases indicating durations or time-related expressions

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

    "For" followed by a duration of time

    np_acts-logits-general · gemini-2.0-flash

    extended periods of time

    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
    ArrowToggle
    -0.76
    
    -0.75
    </thead>
    -0.69
    rrggbb
    -0.68
    +#+#
    -0.67
    Clik
    -0.66
     незавершена
    -0.66
    TERY
    -0.62
    WriteTagHelper
    -0.62
    qrstuvwxyz
    -0.62
    POSITIVE LOGITS
     periods
    0.94
     several
    0.90
     weeks
    0.84
     extended
    0.82
     months
    0.79
     quite
    0.77
     Periods
    0.75
    several
    0.74
     prolonged
    0.73
     years
    0.72
    Activations Density 0.181%

    No Known Activations