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. 10504
    Prev
    Next
    INDEX
    Explanations

    phrases related to memorial services and celebrations of life

    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
    +#+#
    -0.82
    jenost
    -0.79
     InputDecoration
    -0.78
     protoimpl
    -0.70
    stateProvider
    -0.69
    OGND
    -0.69
     lenker
    -0.68
     незавершена
    -0.67
    CppCodeGen
    -0.66
    FontOfSize
    -0.66
    POSITIVE LOGITS
     loving
    0.53
     Dress
    0.45
    Obrázky
    0.44
     future
    0.44
     dress
    0.43
    organiz
    0.43
    loving
    0.43
     heartfelt
    0.42
     memorial
    0.41
    念
    0.41
    Activations Density 0.014%

    No Known Activations