Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14181
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the effort and time needed for tasks or processes

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

    "Takes" followed by temporal or effort-related words

    np_acts-logits-general · gemini-2.0-flash

    takes time and effort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ManagedBean
    -0.58
    >({
    -0.57
    RegressionTest
    -0.54
     MainAxisSize
    -0.53
     VizieR
    -0.52
    InjectAttribute
    -0.50
    اریخ
    -0.50
    TagMode
    -0.50
     بيها
    -0.49
    RRect
    -0.48
    POSITIVE LOGITS
     longer
    1.08
     awhile
    0.94
     effort
    0.93
    longer
    0.82
    effort
    0.80
     patience
    0.78
     forever
    0.78
     moeite
    0.76
     esfuerzo
    0.74
     Longer
    0.72
    Activations Density 0.086%

    No Known Activations