© 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. 6177
    Prev
    Next
    INDEX
    Explanations

    temporal references related to duration and notice periods

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

    Time periods or durations

    np_acts-logits-general · gemini-2.0-flash

    time units and duration

    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
     يتيمه
    -0.79
     Chwiliwch
    -0.59
     تضيفلها
    -0.56
     ligiloj
    -0.53
     الرياضيه
    -0.51
    énario
    -0.51
    WhereInput
    -0.50
    classnames
    -0.50
     esternos
    -0.49
     Waray
    -0.49
    POSITIVE LOGITS
     hábiles
    0.67
     worth
    0.65
     total
    0.64
     consecu
    0.64
    UnusedPrivate
    0.62
     notice
    0.62
     duration
    0.61
    uted
    0.60
     period
    0.60
    간
    0.60
    Activations Density 0.220%

    No Known Activations