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. 23982
    Prev
    Next
    INDEX
    Explanations

    mentions of iTunes and related applications or services

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

    iTunes, Skype, Invitrogen, MTV

    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
    :✨
    -0.54
    ArgsConstructor
    -0.48
    __":
    -0.47
    endphp
    -0.45
    ]")
    -0.43
    __()
    -0.43
    ]');
    -0.43
    semibold
    -0.43
    ]')
    -0.43
    localctx
    -0.42
    POSITIVE LOGITS
     iTunes
    1.21
    iTunes
    1.02
     itunes
    0.96
    itunes
    0.88
    atimes
    0.67
    Tunes
    0.62
    AISSEE
    0.60
     onStop
    0.58
     MTV
    0.56
     onOptions
    0.55
    Activations Density 0.004%

    No Known Activations