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. 10840
    Prev
    Next
    INDEX
    Explanations

    conversations related to complex emotions and moral dilemmas

    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
    лина
    -0.47
     grito
    -0.45
     storici
    -0.43
    CascadeType
    -0.43
    衝
    -0.43
     y
    -0.42
    localVar
    -0.41
    ياء
    -0.40
    GenerationType
    -0.40
     Mean
    -0.39
    POSITIVE LOGITS
     שוליים
    0.92
     nakalista
    0.78
    SequentialGroup
    0.70
     betweenstory
    0.68
     ComVisible
    0.67
    onViewCreated
    0.67
    RenderAtEndOf
    0.67
     Maat
    0.67
    billon
    0.66
    Демографія
    0.66
    Activations Density 0.166%

    No Known Activations