© 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. 24-GEMMASCOPE-RES-16K
    11. 4256
    Prev
    Next
    INDEX
    Explanations

    directives related to training and guidelines for effective communication in emergency health contexts

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

    improvement or expansion

    np_acts-logits-general · gemini-2.0-flash

    improving systems and outcomes

    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
    GEBURTSDATUM
    -0.69
    AnchorStyles
    -0.68
     Rarely
    -0.65
     helplessly
    -0.63
    ForResult
    -0.62
    RectangleBorder
    -0.57
     незавершена
    -0.57
    SCRIBE
    -0.57
    AddTagHelper
    -0.56
     WaitForSeconds
    -0.55
    POSITIVE LOGITS
     increased
    0.99
     improved
    0.97
     strengthening
    0.94
     expanding
    0.91
     expanded
    0.90
     enhanced
    0.86
     expand
    0.85
     strengthened
    0.85
     strengthen
    0.85
     improving
    0.84
    Activations Density 0.271%

    No Known Activations