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. 10-GEMMASCOPE-RES-16K
    6. 12541
    Prev
    Next
    INDEX
    Explanations

    topics related to family planning and harmony in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.58
    ebay
    -0.48
     citer
    -0.48
    libft
    -0.45
     biss
    -0.45
     killed
    -0.44
    UI
    -0.43
    addKeyListener
    -0.43
     dropped
    -0.42
    太
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.77
     ब्रेकडाउन
    0.72
     fieldNum
    0.68
    '])->
    0.67
     ExecuteAsync
    0.66
     INVENTION
    0.63
    }}.
    0.63
    XmlType
    0.62
    cosystem
    0.61
    zupeł
    0.60
    Activations Density 0.462%

    No Known Activations