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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 8718
    Prev
    Next
    INDEX
    Explanations

    terms related to adoption and the process of adopting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.80
     дописавши
    -0.78
    WindowConstants
    -0.75
     שוליים
    -0.69
     Conſ
    -0.67
     Reſ
    -0.67
     CreateTagHelper
    -0.66
    niczka
    -0.66
     précie
    -0.66
     Discogs
    -0.65
    POSITIVE LOGITS
     adopted
    1.73
     adoption
    1.64
     adopt
    1.60
     adopting
    1.57
    adopted
    1.56
     adop
    1.48
    Adop
    1.47
     Adopt
    1.46
     Adop
    1.46
     Adopted
    1.45
    Activations Density 0.201%

    No Known Activations