© 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. 5-GEMMASCOPE-RES-16K
    11. 5136
    Prev
    Next
    INDEX
    Explanations

    phrases related to persistence or remaining in a certain state or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ello
    -0.73
     Dickerson
    -0.72
    Richards
    -0.71
    icu
    -0.68
    icos
    -0.67
     zod
    -0.65
    ici
    -0.64
    pf
    -0.64
    modelName
    -0.64
     cib
    -0.63
    POSITIVE LOGITS
    stay
    2.32
     stay
    2.29
     Stay
    2.13
    Stay
    2.08
    STAY
    2.07
     STAY
    2.02
     stays
    2.00
     stayed
    1.99
     staying
    1.95
     Staying
    1.94
    Activations Density 0.129%

    No Known Activations