© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7750
    Prev
    Next
    INDEX
    Explanations

    references to energy expenditure and caloric intake

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.60
    vode
    -0.44
    AnchorStyles
    -0.44
     initComponents
    -0.43
    IBOutlet
    -0.43
    AndEndTag
    -0.42
     noDo
    -0.42
    parsedMessage
    -0.41
    حوالہ
    -0.41
    endpush
    -0.41
    POSITIVE LOGITS
     spend
    3.30
     spending
    3.25
     spent
    3.06
     spends
    3.02
     Spending
    2.94
     Spend
    2.94
    Spend
    2.89
    Spending
    2.84
    spend
    2.83
     Spent
    2.69
    Activations Density 0.445%

    No Known Activations