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. 13924
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to quality assurances and standards in manufacturing or services

    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
    ftagPool
    -0.73
    enumi
    -0.63
    enumii
    -0.52
    govina
    -0.50
    ">//
    -0.50
    PRWEB
    -0.49
    Fate
    -0.47
    fas
    -0.47
    sizeCache
    -0.46
     _('
    -0.46
    POSITIVE LOGITS
     standards
    2.53
    standards
    2.21
     Standards
    2.07
    Standards
    2.04
     STANDARDS
    2.03
     standard
    1.80
     estándares
    1.61
    standard
    1.60
     STANDARD
    1.56
     standar
    1.55
    Activations Density 0.228%

    No Known Activations