© 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. 3-GEMMASCOPE-RES-16K
    6. 10755
    Prev
    Next
    INDEX
    Explanations

    terms related to promotions and advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ση
    -0.61
    Dieter
    -0.60
     most
    -0.58
     Einstein
    -0.58
    ContentLoaded
    -0.57
    ताब
    -0.57
     
    -0.57
    PointerException
    -0.56
    mtable
    -0.55
    juri
    -0.55
    POSITIVE LOGITS
     promotion
    2.70
     Promotion
    2.45
     promoted
    2.39
     Promote
    2.39
     promoting
    2.35
     promote
    2.35
    promote
    2.29
    Promote
    2.28
    promotion
    2.26
     Promoted
    2.25
    Activations Density 0.053%

    No Known Activations