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. 9126
    Prev
    Next
    INDEX
    Explanations

    phrases related to economics and business practices

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

    following value judgements

    np_acts-logits-general · gemini-2.0-flash

    problems and costs

    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
     المعيارى
    -0.38
     iParam
    -0.35
     запа
    -0.35
    moveToNext
    -0.35
    Välislingid
    -0.33
     resourceCulture
    -0.32
    msgSender
    -0.31
    atchi
    -0.31
    XmlRootElement
    -0.30
     image
    -0.30
    POSITIVE LOGITS
     nakalista
    0.59
    InjectAttribute
    0.58
    ViewInit
    0.55
    legion
    0.46
    ollectionView
    0.46
    😂😂😂😂
    0.45
    sertation
    0.44
    şı
    0.43
     AssemblyTitle
    0.43
    RegressionTest
    0.43
    Activations Density 0.869%

    No Known Activations