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. 4-GEMMASCOPE-RES-16K
    6. 737
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS elements related to stylesheet links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -1.03
    @[+][
    -0.86
    findpost
    -0.81
     &___
    -0.74
     ivelany
    -0.73
     referenties
    -0.72
    :+:
    -0.72
     CreateTagHelper
    -0.67
     EconPapers
    -0.64
    Smarty
    -0.63
    POSITIVE LOGITS
    GetMapping
    1.25
    ViewHolder
    1.14
    fprintf
    1.06
    RequestMapping
    0.92
     fprintf
    0.90
    PostMapping
    0.86
    ToolStrip
    0.73
     ViewHolder
    0.73
    DataGridView
    0.72
     TextStyle
    0.70
    Activations Density 0.020%

    No Known Activations