© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 5042
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and measurements related to experimental conditions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gage
    -0.95
    ,"
    -0.85
    ,»
    -0.83
     geologic
    -0.82
     gray
    -0.81
     fiber
    -0.81
    gray
    -0.79
    
    -0.77
     
    -0.77
     plow
    -0.74
    POSITIVE LOGITS
    ”,
    0.83
    łam
    0.82
     mum
    0.82
     yoghurt
    0.80
     grey
    0.78
     aeroplane
    0.78
    varepsilon
    0.77
    ”.
    0.76
     ∆
    0.76
     judgement
    0.76
    Activations Density 1.430%

    No Known Activations