© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 323
    Prev
    Next
    INDEX
    Explanations

    references to legal standards and numerical data in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tomorrow
    -0.55
    cillor
    -0.54
    cog
    -0.53
     sosten
    -0.52
     torch
    -0.52
     Stra
    -0.51
    ricts
    -0.49
     nik
    -0.48
    ivent
    -0.47
     grab
    -0.47
    POSITIVE LOGITS
    MLLoader
    0.83
    ContentAsync
    0.75
     CHAPITRE
    0.66
    CodedInputStream
    0.66
     habet
    0.65
    Personensuche
    0.64
    labus
    0.64
     pleaſure
    0.63
    Переваги
    0.63
    bootstrapcdn
    0.60
    Activations Density 0.459%

    No Known Activations