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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4057
    Prev
    Next
    INDEX
    Explanations

    underscore-prefixed variables commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.59
    bitField
    -0.55
    XmlAccessorType
    -0.55
    jsxFileName
    -0.54
     réf
    -0.52
     AssemblyProduct
    -0.51
    homonymie
    -0.50
    ποτε
    -0.49
    weza
    -0.48
     dési
    -0.48
    POSITIVE LOGITS
     greateſt
    0.68
     Chriftian
    0.66
    gerald
    0.66
     iſt
    0.65
     fevere
    0.64
     ſmall
    0.63
     виправивши
    0.62
    ſelves
    0.62
     ſtre
    0.61
    ſelf
    0.61
    Activations Density 0.221%

    No Known Activations