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. 9-GEMMASCOPE-RES-16K
    6. 6849
    Prev
    Next
    INDEX
    Explanations

    references to energy prices and related issues

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

    Energy companies or suppliers

    np_acts-logits-general · gemini-2.0-flash

    energy prices and suppliers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.58
    Tikang
    -0.57
     nahilalakip
    -0.55
     Administrativna
    -0.54
    interopRequire
    -0.47
    oa̍t
    -0.46
    lardır
    -0.46
    fjspx
    -0.45
     calendriers
    -0.45
     reuniones
    -0.44
    POSITIVE LOGITS
     Energy
    0.37
     energy
    0.35
    ChildScrollView
    0.34
     ENERGY
    0.34
    PreferredItem
    0.33
    energy
    0.33
    Dif
    0.32
     Energi
    0.31
    Energy
    0.31
    compare
    0.31
    Activations Density 0.175%

    No Known Activations