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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9506
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to equations and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    |@
    -0.55
     CreateTagHelper
    -0.55
    ∩
    -0.54
    %@
    -0.53
    %@",
    -0.51
     AssemblyTitle
    -0.51
    Way
    -0.50
    ſelf
    -0.50
    +#+#
    -0.49
    )//
    -0.48
    POSITIVE LOGITS
    \[
    1.12
    SequentialGroup
    0.94
    TagMode
    0.87
    SourceChecksum
    0.83
    RectangleBorder
    0.67
     صوتيه
    0.62
     مشين
    0.62
     الرياضيه
    0.60
     ISNI
    0.60
     AssemblyVersion
    0.58
    Activations Density 0.138%

    No Known Activations