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. 20-GEMMASCOPE-RES-16K
    6. 13643
    Prev
    Next
    INDEX
    Explanations

    subjective opinions and questions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.80
    bootstrapcdn
    -0.68
    XmlAccessType
    -0.65
     EconPapers
    -0.63
     Wiktionnaire
    -0.61
    はじめに
    -0.60
    LLocation
    -0.59
    GEBURTS
    -0.58
    发表于
    -0.56
    GOTREF
    -0.56
    POSITIVE LOGITS
     WRONG
    1.18
     Wrong
    1.16
    Wrong
    1.15
     wrong
    1.08
    WRONG
    1.03
     Nope
    1.01
    wrong
    1.00
     untrue
    0.96
     incorrect
    0.94
     nope
    0.94
    Activations Density 0.280%

    No Known Activations