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. 20-GEMMASCOPE-RES-16K
    6. 2220
    Prev
    Next
    INDEX
    Explanations

    tags and configuration elements typically used in XML for defining beans in a Spring framework context

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

    XML or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    spring configuration

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    DeleteBehavior
    -0.63
    PreferredItem
    -0.56
    .$,
    -0.52
     Samuels
    -0.52
    WithEmail
    -0.51
    MessageState
    -0.49
    LayoutStyle
    -0.49
    ciera
    -0.49
     crash
    -0.48
    sizeCache
    -0.48
    POSITIVE LOGITS
     spring
    0.78
    Spring
    0.71
     Spring
    0.70
    spring
    0.69
     SPRING
    0.66
     springtime
    0.64
    springs
    0.62
     AssemblyProduct
    0.61
     springs
    0.59
    SPRING
    0.58
    Activations Density 0.127%

    No Known Activations