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

    Neuronpedia

    APICircuit 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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 993
    Prev
    Next
    INDEX
    Explanations

    sections and terms related to materials and methods in scientific research

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

    occurrences of the word "and" related to methodologies or materials in scientific writing

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

    Materials and Methods sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Matériau
    -1.14
    Material
    -1.09
     MATERIAL
    -1.07
     Material
    -1.06
     Mater
    -1.03
    material
    -1.01
     material
    -1.00
     Материал
    -1.00
    MATERIAL
    -0.99
     materialism
    -0.98
    POSITIVE LOGITS
     Moh
    0.44
    indakan
    0.42
     Sunni
    0.41
     McKenzie
    0.40
     Zacks
    0.40
    pandora
    0.39
    genome
    0.38
     InkWell
    0.38
    eckel
    0.37
    aksikan
    0.37
    Activations Density 0.042%

    No Known Activations