© 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. 2-GEMMASCOPE-RES-16K
    6. 6054
    Prev
    Next
    INDEX
    Explanations

    dates and references to the month of March

    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
    InjectAttribute
    -0.82
     Ferdinando
    -0.82
     myſelf
    -0.82
     playmobil
    -0.80
    }$​
    -0.80
     للتو
    -0.78
     Diſ
    -0.78
     Monfieur
    -0.77
     Inſ
    -0.75
     Cowan
    -0.74
    POSITIVE LOGITS
     March
    3.37
    March
    3.14
     MARCH
    2.85
    MARCH
    2.62
     march
    2.53
    march
    2.40
     marzo
    2.05
     Marches
    1.97
     maart
    1.84
     marches
    1.80
    Activations Density 0.046%

    No Known Activations