© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 967
    Prev
    Next
    INDEX
    Explanations

    patterns and rules related to URL structures and regular expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -1.09
    LookAnd
    -1.00
     >=",
    -0.86
     виправивши
    -0.86
    RenderAtEndOf
    -0.85
     snippetHide
    -0.83
     saites
    -0.79
    :✨
    -0.77
     mergeFrom
    -0.77
    ///</
    -0.77
    POSITIVE LOGITS
    ,
    0.59
    "
    0.53
     others
    0.52
     I
    0.52
     δε
    0.51
    *
    0.50
     men
    0.50
    ...
    0.49
     second
    0.49
     s
    0.49
    Activations Density 0.208%

    No Known Activations