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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114632
    Prev
    Next
    INDEX
    Explanations

    interactions related to programming options and parameters

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

    Object or variable references in programming code that are being accessed for their properties, methods, or values.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     různých
    -0.33
     forskjellige
    -0.29
     vēl
    -0.28
     élément
    -0.28
     Suomessa
    -0.27
     cálido
    -0.27
     provisoire
    -0.27
     trône
    -0.26
     forskellige
    -0.26
     emprego
    -0.26
    POSITIVE LOGITS
    LEncoder
    0.95
     Majefty
    0.92
    
    0.91
    featureID
    0.91
    <unused74>
    0.89
    <unused43>
    0.89
    <unused23>
    0.89
    <unused41>
    0.88
    <unused8>
    0.88
    <pad>
    0.88
    Activations Density 0.041%

    No Known Activations