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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6796
    Prev
    Next
    INDEX
    Explanations

    references to stylesheets in HTML documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to stylesheets in HTML documents

    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
    FormTagHelper
    -0.70
    getContentPane
    -0.56
    HttpGet
    -0.56
    exitRule
    -0.44
    ❋
    -0.41
    setzung
    -0.41
     jdbcTemplate
    -0.40
    野球
    -0.40
    xAxis
    -0.40
    issauga
    -0.39
    POSITIVE LOGITS
    TagHelpers
    1.90
    CodeAttribute
    1.46
    ValueStyle
    1.42
    AddTagHelper
    1.35
    EndInit
    1.11
    IUrlHelper
    1.11
     يتيمه
    1.10
    GOTREF
    1.08
     nahilalakip
    1.08
    LookAnd
    1.04
    Activations Density 0.012%

    No Known Activations