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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 419
    Prev
    Next
    INDEX
    Explanations

    references to variable names and parameters in programming code

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

    coordinates and simple calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     furiously
    -0.51
     blindly
    -0.51
     noiva
    -0.50
     senhora
    -0.50
     needlessly
    -0.49
     backwards
    -0.49
    Serviço
    -0.47
     confidently
    -0.47
     configured
    -0.46
     nobre
    -0.46
    POSITIVE LOGITS
    StructEnd
    0.89
    styleType
    0.80
    ftagPool
    0.79
     purpoſe
    0.74
     pleaſure
    0.72
     Wikimedijinoj
    0.71
    postIndex
    0.70
    oredCriteria
    0.69
     betweenstory
    0.68
    expandindo
    0.66
    Activations Density 0.031%

    No Known Activations