© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10833
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to malice and evidence requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.66
    iNdEx
    -0.63
    Aholisi
    -0.63
    SBATCH
    -0.55
    bootstrapcdn
    -0.54
    UnifiedTopology
    -0.53
    icana
    -0.52
    rceil
    -0.50
    getDoctrine
    -0.49
    
    -0.49
    POSITIVE LOGITS
     facts
    0.76
     probar
    0.69
     proof
    0.67
     preponderance
    0.66
     prima
    0.66
     prova
    0.64
    facts
    0.63
     preuve
    0.63
     للمعارف
    0.62
     elements
    0.60
    Activations Density 3.139%

    No Known Activations