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. 14159
    Prev
    Next
    INDEX
    Explanations

    topics related to leadership styles and their impact on job satisfaction in healthcare professionals

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

    followed by "is" or "the"

    np_acts-logits-general · gemini-2.0-flash

    describes consequences or states

    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
     disambiguazione
    -0.80
     nakalista
    -0.76
     YOUR
    -0.73
     дописавши
    -0.70
     bikin
    -0.67
     Your
    -0.66
     —
    -0.65
     YOU
    -0.65
     Assn
    -0.64
    Your
    -0.64
    POSITIVE LOGITS
    ‟
    0.67
     interrelated
    0.56
     perceives
    0.56
     consequently
    0.56
     implication
    0.56
    ">';
    0.55
     hege
    0.55
     perceptions
    0.55
     Obwohl
    0.55
     perceive
    0.55
    Activations Density 0.414%

    No Known Activations