© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15129
    Prev
    Next
    INDEX
    Explanations

    the presence of main function definitions in various programming languages

    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
     يتيمه
    -0.61
     newOwner
    -0.58
     defaultstate
    -0.58
    ViewImports
    -0.56
    slidesToShow
    -0.56
     FetchType
    -0.55
    Vorlage
    -0.55
     arşivlendi
    -0.55
    NOPQRST
    -0.55
     pinulongan
    -0.55
    POSITIVE LOGITS
    __':
    1.26
    __':
    1.20
    __":
    1.13
    __":
    1.10
    IUrlHelper
    0.88
    GEBURTS
    0.60
    Portale
    0.54
     kasarigan
    0.54
    ngOnInit
    0.52
     bezeichneter
    0.50
    Activations Density 0.030%

    No Known Activations