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 - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 5293
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to warranties and their disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.82
    FormTagHelper
    -0.80
    titleMargin
    -0.73
    IVEREF
    -0.70
    IonicModule
    -0.69
     nonUne
    -0.65
     himo
    -0.63
    NameInMap
    -0.63
    Spoljašnje
    -0.62
     '\\;'
    -0.62
    POSITIVE LOGITS
    PREFERRED
    4.01
    Preferred
    1.44
     Preferred
    1.43
     preferred
    1.41
    preferred
    1.33
    REFERRED
    1.00
    enumii
    0.88
     preferable
    0.81
    setPreferred
    0.80
    Preferences
    0.80
    Activations Density 0.004%

    No Known Activations