© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and events related to statistics or measures

    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
     generations
    -0.56
     Camer
    -0.52
     cục
    -0.51
     gener
    -0.50
     hum
    -0.50
    mparas
    -0.49
    plom
    -0.49
     Функ
    -0.49
     INCORPOR
    -0.49
    ItemList
    -0.49
    POSITIVE LOGITS
    AndEndTag
    1.12
     <=",
    1.07
    SharedCtor
    0.97
    NameInMap
    0.94
     @"/
    0.92
    matchCondition
    0.88
    UnusedPrivate
    0.88
    ]")]
    0.84
    PerformLayout
    0.83
    出版年
    0.82
    Activations Density 0.167%

    No Known Activations