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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 30359
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to ownership and transfer of titles

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

    legal ownership and title

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    ⓧ
    -0.63
     nonUne
    -0.58
    adpleegd
    -0.58
    featureID
    -0.57
     ChromeDriver
    -0.56
    FontOfSize
    -0.55
    machines
    -0.55
    machine
    -0.54
     gyhoeddwyd
    -0.54
    ChildScrollView
    -0.52
    POSITIVE LOGITS
     ownership
    0.93
     Ownership
    0.77
    Ownership
    0.75
    ownership
    0.68
     owner
    0.53
     owners
    0.48
     Besitz
    0.48
     possession
    0.45
     rights
    0.42
     Owner
    0.42
    Activations Density 0.037%

    No Known Activations