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. 11-GEMMASCOPE-RES-16K
    6. 5979
    Prev
    Next
    INDEX
    Explanations

    references to supplementary material and corrections in academic articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.64
    gorov
    -0.55
    ึ้น
    -0.52
    נפ
    -0.48
    verwijspagina
    -0.48
    CELLANEOUS
    -0.48
    MigrationBuilder
    -0.47
    thand
    -0.47
    queryset
    -0.47
    ...</
    -0.46
    POSITIVE LOGITS
    FormTagHelper
    0.70
    addContainerGap
    0.67
    MemoryWarning
    0.67
     initComponents
    0.63
    rtype
    0.61
    SourceChecksum
    0.60
    Personensuche
    0.59
     CURIAM
    0.56
    脚注の使い方
    0.56
     MainAxisSize
    0.55
    Activations Density 0.460%

    No Known Activations