Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7886
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JavaScript function definitions

    np_acts-logits-general · gemini-2.0-flash

    function(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.98
    
    -0.96
    AndEndTag
    -0.88
    +:+
    -0.83
    ollectionView
    -0.81
     Normdatei
    -0.81
     surla
    -0.80
    HttpPut
    -0.80
    httphttps
    -0.78
    HasAnnotation
    -0.77
    POSITIVE LOGITS
    (){
    0.81
     ()
    0.77
    ()
    0.69
     (
    0.55
    (
    0.50
    callee
    0.50
    (){
    
    0.49
    (_
    0.48
     (){
    0.48
     (_
    0.45
    Activations Density 0.029%

    No Known Activations