© 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. 1-GEMMASCOPE-RES-16K
    6. 5105
    Prev
    Next
    INDEX
    Explanations

    the word "last" indicating instances or references to timeframes or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ยว
    -0.53
     Witherspoon
    -0.52
    reuth
    -0.51
     kaw
    -0.50
     Poole
    -0.49
     transparent
    -0.47
    aventura
    -0.47
    værende
    -0.47
    })));
    -0.46
     mente
    -0.46
    POSITIVE LOGITS
     last
    1.91
     Last
    1.33
    Last
    1.30
    last
    1.27
     LAST
    1.24
     laft
    1.16
     förra
    1.13
     laſt
    1.11
     lasts
    1.10
     letzte
    1.05
    Activations Density 0.092%

    No Known Activations