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. 4266
    Prev
    Next
    INDEX
    Explanations

    references to the concept of time, particularly focusing on the word "late."

    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
    RenderAtEndOf
    -0.67
    interopRequire
    -0.66
    èdia
    -0.62
     &___
    -0.60
    })]
    -0.59
     Seeder
    -0.59
    𝓈
    -0.58
    rostis
    -0.57
    riwal
    -0.56
     relever
    -0.56
    POSITIVE LOGITS
     late
    3.90
    Late
    3.56
     Late
    3.55
     LATE
    3.47
    late
    3.29
    LATE
    3.07
     spät
    1.81
     tard
    1.59
    lates
    1.57
     póź
    1.44
    Activations Density 0.056%

    No Known Activations