© 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. 10-GEMMASCOPE-RES-16K
    11. 1652
    Prev
    Next
    INDEX
    Explanations

    terms related to decomposition and splitting in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    requipa
    -0.47
    fır
    -0.45
    ghold
    -0.43
    omalainen
    -0.43
    WAUKEE
    -0.42
    tioners
    -0.42
     firm
    -0.42
    hithe
    -0.42
    potranspiration
    -0.42
     бор
    -0.41
    POSITIVE LOGITS
     splits
    1.12
     splitting
    1.11
    Split
    1.07
     Split
    1.06
     split
    1.06
     partitioned
    1.04
    split
    1.02
     breakup
    0.98
     parted
    0.93
     splitter
    0.93
    Activations Density 0.625%

    No Known Activations