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. 2-GEMMASCOPE-RES-16K
    6. 6653
    Prev
    Next
    INDEX
    Explanations

    phrases related to establishing rules or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.79
    DoubleQuotes
    -0.79
    phism
    -0.77
    Personensuche
    -0.77
    tagHelperRunner
    -0.76
    Vidite
    -0.74
    )}]{
    -0.68
    onded
    -0.68
     StatelessWidget
    -0.67
    Abit
    -0.67
    POSITIVE LOGITS
     setting
    1.48
     Setting
    1.31
    Setting
    1.29
     SETTING
    1.23
    setting
    1.14
     set
    1.08
     settings
    1.05
    SETTING
    1.04
     Settings
    0.95
    Settings
    0.95
    Activations Density 0.155%

    No Known Activations