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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9411
    Prev
    Next
    INDEX
    Explanations

    references to specific names, organizations, and terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     soeur
    -0.51
    JsonKey
    -0.48
     sœur
    -0.45
     scatola
    -0.45
     mücade
    -0.44
     gué
    -0.44
     toată
    -0.44
    ixon
    -0.43
     adipis
    -0.43
     ürünleri
    -0.43
    POSITIVE LOGITS
     تضيفلها
    1.00
    endphp
    0.68
    tagHelperRunner
    0.67
    دانشنامهٔ
    0.64
    ngOnInit
    0.63
    μως
    0.63
    //{
    0.60
    érité
    0.60
     bezeichneter
    0.59
    FTFY
    0.57
    Activations Density 1.256%

    No Known Activations