© 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. 23-GEMMASCOPE-RES-16K
    11. 15136
    Prev
    Next
    INDEX
    Explanations

    syntax elements within programming code, particularly focusing on function calls and object structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ​
    -0.62
     
    -0.61
     ​
    -0.60
    <b>
    -0.58
       
    -0.55
    ↵↵
    -0.54
    <u>
    -0.53
    \\
    -0.50
     el
    -0.50
    ↵↵↵
    -0.49
    POSITIVE LOGITS
    AndEndTag
    1.05
     للاسماء
    1.01
     SIMBAD
    0.92
     للمعارف
    0.91
    \<^
    0.90
     Administrativna
    0.89
    ValueStyle
    0.89
    >\<^
    0.88
    AddTagHelper
    0.87
    sizeCache
    0.87
    Activations Density 0.081%

    No Known Activations