© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3734
    Prev
    Next
    INDEX
    Explanations

    terms related to advancements and progress 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 @ 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
    wußt
    -0.62
    UTERS
    -0.60
     kasarigan
    -0.59
    IZONTAL
    -0.57
    ropical
    -0.57
    ském
    -0.56
     joaat
    -0.56
     esternos
    -0.55
     '\\;'
    -0.54
     nhàng
    -0.52
    POSITIVE LOGITS
     advances
    1.56
     advancement
    1.47
     advance
    1.47
     progress
    1.47
     Advance
    1.44
     advancing
    1.44
    advance
    1.42
    Advance
    1.40
    progress
    1.33
     advancements
    1.33
    Activations Density 0.342%

    No Known Activations