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. 2331
    Prev
    Next
    INDEX
    Explanations

    specific biological and medical processes related to genes and their expression during infections

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

    followed by "during"

    np_acts-logits-general · gemini-2.0-flash

    during

    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
    
    -0.76
    servable
    -0.66
    isielt
    -0.61
    +#+#
    -0.61
    cuerdo
    -0.59
    resiasi
    -0.58
     actualidad
    -0.55
    neum
    -0.55
     EconPapers
    -0.55
    ształ
    -0.53
    POSITIVE LOGITS
     during
    3.46
    during
    2.97
     During
    2.72
     DURING
    2.69
     durante
    2.69
    During
    2.67
     tijdens
    2.40
    durante
    2.27
    Durante
    2.15
     während
    2.10
    Activations Density 1.134%

    No Known Activations