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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1614
    Prev
    Next
    INDEX
    Explanations

    phrases related to food preparation and portion control

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

    manageability or being overwhelmed

    np_acts-logits-general · gemini-2.0-flash

    overwhelmed or manageable amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.68
    addCriterion
    -0.61
    httphttps
    -0.56
    hubanes
    -0.56
    BindView
    -0.55
    +#+#
    -0.54
    DataURL
    -0.53
    Тарихы
    -0.51
    üttel
    -0.51
     defStyle
    -0.51
    POSITIVE LOGITS
     manageable
    1.35
     overwhelm
    0.76
     doable
    0.76
     daunting
    0.75
     AssemblyCulture
    0.74
     manag
    0.72
    ageable
    0.71
     easier
    0.70
     overload
    0.70
    Easier
    0.69
    Activations Density 0.280%

    No Known Activations