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. 5-GEMMASCOPE-RES-16K
    6. 13003
    Prev
    Next
    INDEX
    Explanations

    verbs related to assessment and analysis processes

    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
    -
    -0.70
    leby
    -0.54
    flashdata
    -0.52
     MonoBehaviour
    -0.52
    delli
    -0.51
    ModelState
    -0.50
     Me
    -0.49
    PickerController
    -0.48
    RequiresApi
    -0.48
    厘
    -0.47
    POSITIVE LOGITS
    Jeografia
    0.85
     itſelf
    0.79
     Wikimedijinoj
    0.79
     ―――――
    0.77
     isInitialized
    0.76
     }}"></
    0.74
    AddTagHelper
    0.74
     الفلك
    0.73
     uſed
    0.71
    BibitemShut
    0.70
    Activations Density 1.202%

    No Known Activations