Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2854
    Prev
    Next
    INDEX
    Explanations

    technical references to coding or software processes

    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
     Anſ
    -1.07
     Monfieur
    -1.03
     déchir
    -1.03
     ་་
    -1.01
     myſelf
    -1.01
     doubtnut
    -1.01
     nahilalakip
    -0.98
    berdayakan
    -0.97
     itſelf
    -0.96
     Majefty
    -0.95
    POSITIVE LOGITS
     Nowadays
    1.04
     nowadays
    0.96
     advices
    0.94
    Nowadays
    0.92
     Moreover
    0.85
     «
    0.83
    Moreover
    0.78
    ´
    0.77
     ressources
    0.73
     „
    0.72
    Activations Density 6.128%

    No Known Activations