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. 25-GEMMASCOPE-RES-16K
    6. 8002
    Prev
    Next
    INDEX
    Explanations

    specific references to parts of plants or botanical components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berdayakan
    -0.20
     varandra
    -0.19
     vägen
    -0.19
     zijne
    -0.18
     creș
    -0.18
     stället
    -0.18
     salvación
    -0.17
     ansik
    -0.17
     noastră
    -0.17
     göm
    -0.17
    POSITIVE LOGITS
    chman
    0.48
    rion
    0.48
    ience
    0.48
    atier
    0.46
    roni
    0.46
    arie
    0.46
    kers
    0.45
    livan
    0.45
    leman
    0.45
    kovich
    0.45
    Activations Density 27.780%

    No Known Activations