© 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. 14294
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific terms and acronyms related to health and biology

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

    Tokens followed by file access operations

    np_acts-logits-general · gemini-2.0-flash

    Occupational Safety, Oxera

    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
     AssemblyTitle
    -0.68
     optimal
    -0.56
     operational
    -0.53
    Архівовано
    -0.53
     operation
    -0.52
     oral
    -0.51
    optimize
    -0.51
    Operational
    -0.50
     opera
    -0.50
    ември
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.62
     crossorigin
    0.61
     pép
    0.60
    ThroughAttribute
    0.59
     moelle
    0.59
    setVerticalGroup
    0.59
     combien
    0.59
     henvisninger
    0.58
     yhte
    0.58
     InputDecoration
    0.58
    Activations Density 0.389%

    No Known Activations