© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    connections and interactions through specific historical events and innovations

    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
     themſelves
    -0.95
     ostavi
    -0.87
     purpoſe
    -0.87
    Билгалдахарш
    -0.84
     itſelf
    -0.83
     thither
    -0.83
     Majefty
    -0.81
     preſent
    -0.80
     تانيه
    -0.80
     poffible
    -0.80
    POSITIVE LOGITS
     erstmals
    0.51
     again
    0.47
     wieder
    0.42
    MediaStore
    0.40
     D
    0.40
    again
    0.40
    மே
    0.39
     &
    0.38
     by
    0.37
    なかったので
    0.37
    Activations Density 0.974%

    No Known Activations