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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2361
    Prev
    Next
    INDEX
    Explanations

    references to "base" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.86
     paja
    -0.80
     NSCoder
    -0.69
     McQu
    -0.68
    СТВ
    -0.64
     écl
    -0.64
     VICT
    -0.63
     emballage
    -0.63
    publique
    -0.62
    loroethene
    -0.60
    POSITIVE LOGITS
     bases
    1.85
     base
    1.85
     Bases
    1.72
    Bases
    1.70
     Base
    1.68
     BAS
    1.65
    bases
    1.62
     BASE
    1.59
    BAS
    1.55
    base
    1.55
    Activations Density 0.091%

    No Known Activations