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. 7609
    Prev
    Next
    INDEX
    Explanations

    terms related to serial communication and serialization in programming

    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
     Athene
    -0.95
    ArrowToggle
    -0.86
    modelBuilder
    -0.86
     PNC
    -0.84
     تضيفلها
    -0.83
    AnchorTagHelper
    -0.81
    Personendaten
    -0.81
    strophy
    -0.81
    basicConfig
    -0.81
     Ephraim
    -0.80
    POSITIVE LOGITS
     SERIAL
    1.43
     Serial
    1.37
    Serial
    1.35
    SERIAL
    1.30
    ser
    1.29
     ser
    1.26
    Ser
    1.25
     Serializable
    1.25
     Ser
    1.25
     serial
    1.23
    Activations Density 0.136%

    No Known Activations