© 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. 1-GEMMASCOPE-RES-16K
    11. 11082
    Prev
    Next
    INDEX
    Explanations

    parentheses and various nested function calls or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.59
    ↵
    -0.50
      
    -0.45
    -
    -0.42
    <eos>
    -0.41
    (
    -0.39
    t
    -0.38
    3
    -0.38
    ;
    -0.38
     (
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    1.25
    extAlignment
    1.20
     ModelExpression
    1.14
    awtextra
    1.11
    VersionUID
    1.10
     мәкал
    1.09
     المعيارى
    1.05
     CURIAM
    1.05
    IndentedString
    1.05
    AndEndTag
    1.03
    Activations Density 0.165%

    No Known Activations