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. 20-GEMMASCOPE-RES-16K
    6. 1415
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to file formats and audio conversion processes

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

    File formats or data formats

    np_acts-logits-general · gemini-2.0-flash

    file formats

    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
    AndEndTag
    -0.79
     cref
    -0.76
     Insee
    -0.68
     AssemblyCompany
    -0.66
     CreateTagHelper
    -0.57
     betweenstory
    -0.57
    پیوند
    -0.53
    AnchorStyles
    -0.52
     DbSet
    -0.51
    nonatomic
    -0.51
    POSITIVE LOGITS
     formats
    1.66
     format
    1.62
     Formats
    1.46
     formatos
    1.41
    format
    1.41
     Format
    1.37
    Format
    1.35
     formato
    1.33
    formats
    1.30
     FORMAT
    1.29
    Activations Density 0.454%

    No Known Activations