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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2139
    Prev
    Next
    INDEX
    Explanations

    specific patterns and references related to programming and coding constructs, particularly in relation to nested structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.63
     sumpay
    -0.63
     kasarigan
    -0.51
     Photocase
    -0.51
     queſta
    -0.50
     Chwiliwch
    -0.48
    رشف
    -0.47
    !*\
    -0.47
    ztes
    -0.47
    RTDA
    -0.46
    POSITIVE LOGITS
    ="+
    1.84
    ='+
    0.82
    ="-
    0.79
    :"+
    0.72
     "+
    0.71
    "+
    0.70
    -"+
    0.68
    ("+
    0.66
    >"+
    0.65
    ValueStyle
    0.65
    Activations Density 0.015%

    No Known Activations