© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11482
    Prev
    Next
    INDEX
    Explanations

    the term "ultimate" in various contexts indicating finality or the highest level of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.93
     ExecuteAsync
    -0.65
    janya
    -0.64
     BoxDecoration
    -0.62
     Negra
    -0.61
     einges
    -0.59
    setColumns
    -0.58
    ก่
    -0.58
     Pron
    -0.56
    normals
    -0.56
    POSITIVE LOGITS
     ultimate
    1.52
    ultimate
    1.47
    Ultimate
    1.40
     Ultimate
    1.38
     ULT
    1.29
     ulti
    1.07
    ulti
    0.97
     ultimately
    0.96
     Ul
    0.91
     Ultimately
    0.88
    Activations Density 0.138%

    No Known Activations