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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16368
    Prev
    Next
    INDEX
    Explanations

    references to elements and compounds related to chemistry or biology

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

    ending in "lag", "rm", "=," or "Eng"

    np_acts-logits-general · gemini-2.0-flash

    flagellar or el

    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
    참고
    -0.68
     يتيمه
    -0.66
    
    -0.61
     AssemblyVersion
    -0.57
    CodeAttribute
    -0.55
    تقاوى
    -0.53
     vVar
    -0.52
    CloseOperation
    -0.52
     Pent
    -0.51
    StoryboardSegue
    -0.51
    POSITIVE LOGITS
     el
    3.01
     El
    2.97
    El
    2.89
    el
    2.59
     EL
    2.44
    EL
    2.40
    els
    1.84
    ELS
    1.72
     Эль
    1.68
     els
    1.64
    Activations Density 0.557%

    No Known Activations