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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15087
    Prev
    Next
    INDEX
    Explanations

    patterns in structured data, particularly related to object keys and values in programming syntax

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

    Code snippets and array definitions

    np_acts-logits-general · gemini-2.0-flash

    code and data snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.82
     EconPapers
    -0.80
     Kräfte
    -0.71
     queſta
    -0.68
     utafitiHapana
    -0.65
    (',');
    -0.63
     morire
    -0.62
     Italij
    -0.61
    ""}
    -0.59
     getItemCount
    -0.58
    POSITIVE LOGITS
    jsxFileName
    0.52
    、
    0.39
    dimethy
    0.38
     termed
    0.38
     Scooby
    0.37
     Aad
    0.36
    Rptr
    0.36
    적으로
    0.35
     containing
    0.35
    ,
    
    0.34
    Activations Density 0.182%

    No Known Activations