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. 3894
    Prev
    Next
    INDEX
    Explanations

    references to lawn care and fertilizer applications

    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
     typelib
    -0.73
    DotNetBar
    -0.72
    sizeCache
    -0.68
     nahilalakip
    -0.65
    rungsseite
    -0.58
    CloseOperation
    -0.57
    DialogComponent
    -0.56
    simpleType
    -0.56
     виправивши
    -0.55
    GraphicsUnit
    -0.54
    POSITIVE LOGITS
     grass
    1.35
     lawn
    1.27
     lawns
    1.17
     Grass
    1.12
     mowing
    1.12
    grass
    1.11
     turf
    1.10
     Lawn
    1.10
     mow
    1.09
    Grass
    1.07
    Activations Density 0.168%

    No Known Activations