© 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. 11868
    Prev
    Next
    INDEX
    Explanations

    terms related to duration and longevity

    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
     Houſe
    -0.65
     houſe
    -0.64
     reaſon
    -0.60
     Мексичка
    -0.59
     preſent
    -0.58
    énario
    -0.58
    REQUENCY
    -0.58
     okuyayım
    -0.57
    lichung
    -0.57
     thereto
    -0.57
    POSITIVE LOGITS
     lasting
    1.53
     lasted
    1.50
     lasts
    1.44
    lasting
    1.43
     Lasting
    1.38
    DUR
    1.31
     DUR
    1.30
     dura
    1.28
     durar
    1.19
     durata
    1.16
    Activations Density 0.183%

    No Known Activations