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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12904
    Prev
    Next
    INDEX
    Explanations

    mentions of financial incentives and tax abatements in relation to development projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    CppMethod
    -0.30
    WebControls
    -0.30
     Democrá
    -0.29
     prévention
    -0.28
    зап
    -0.28
    parsedMessage
    -0.27
    曖昧さ回避
    -0.27
    cuadro
    -0.26
     onBind
    -0.26
    аз
    -0.26
    POSITIVE LOGITS
     незавершена
    0.77
     boosters
    0.73
    AndEndTag
    0.60
     booster
    0.59
    booster
    0.59
     competitiveness
    0.58
    taxes
    0.56
    industrial
    0.55
     atraer
    0.55
    incenti
    0.55
    Activations Density 0.169%

    No Known Activations