© 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. 4036
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related connective words indicating relationships between concepts or clauses

    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
    asker
    -0.53
     זכ
    -0.50
    記
    -0.49
    stad
    -0.48
    ほどの
    -0.48
    vara
    -0.47
    逆
    -0.47
     MÉ
    -0.46
     ör
    -0.46
    Smack
    -0.46
    POSITIVE LOGITS
    principalTable
    0.89
     autorytatywna
    0.85
    MigrationBuilder
    0.75
    usermodel
    0.68
     فريبيس
    0.65
    efeated
    0.62
     يتيمه
    0.61
    Parcelize
    0.61
    كتشاف
    0.61
     insuffisamment
    0.60
    Activations Density 0.311%

    No Known Activations