© 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. 22-GEMMASCOPE-RES-16K
    11. 8134
    Prev
    Next
    INDEX
    Explanations

    phrases related to timelines and punctuality in various contexts

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

    timeliness or punctuality

    np_acts-logits-general · gemini-2.0-flash

    timeliness and promptness

    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
    SourceChecksum
    -0.87
    __':
    -0.85
    IUrlHelper
    -0.82
    __':
    -0.80
    __":
    -0.80
    enumi
    -0.80
    exitRule
    -0.80
    WireFormatLite
    -0.79
     <<<<<<<<<<<<<<
    -0.73
     resourceCulture
    -0.72
    POSITIVE LOGITS
     timely
    1.59
    timely
    1.20
     punct
    1.15
     Timely
    1.15
     punctual
    1.09
    punct
    0.98
     promptly
    0.95
     tepat
    0.93
     prompt
    0.92
    prompt
    0.91
    Activations Density 0.172%

    No Known Activations