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. 16-GEMMASCOPE-RES-16K
    6. 32
    Prev
    Next
    INDEX
    Explanations

    references to organizations and journals related to specific fields or topics

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

    time or frequency

    np_acts-logits-general · gemini-2.0-flash

    frequency or regularity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prochains
    -0.58
     AssemblyCulture
    -0.57
    CreateModel
    -0.55
     inaugural
    -0.54
    sizeCache
    -0.52
     initial
    -0.52
     viewDidLoad
    -0.50
    これまでの
    -0.50
    acakt
    -0.49
     tadi
    -0.49
    POSITIVE LOGITS
     annually
    1.23
     yearly
    1.18
     routinely
    1.12
     regularly
    1.10
     often
    1.04
     occasionally
    1.02
     monthly
    1.01
     usually
    0.99
     sometimes
    0.99
     weekly
    0.99
    Activations Density 0.585%

    No Known Activations