© 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. 3-GEMMASCOPE-RES-16K
    11. 11487
    Prev
    Next
    INDEX
    Explanations

    complex syntactical structures involving modal verbs in German

    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
    enosine
    -0.66
    haften
    -0.54
    zeichneten
    -0.54
    ="//
    -0.53
    φέ
    -0.52
    *}$
    -0.52
     [],
    -0.51
     [{
    -0.50
     Vle
    -0.50
     viri
    -0.49
    POSITIVE LOGITS
    twimg
    0.76
    IsPostBack
    0.70
     Désolé
    0.68
    mergeFrom
    0.68
    ForValue
    0.66
     ProtoMessage
    0.65
    bayaran
    0.64
    nito
    0.64
    SerializedName
    0.62
     resourceCulture
    0.62
    Activations Density 0.182%

    No Known Activations