© 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. 14-GEMMASCOPE-RES-16K
    11. 3965
    Prev
    Next
    INDEX
    Explanations

    language related to societal structures and improvements in systems over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.58
    \{\\
    -0.58
     Orto
    -0.56
     iprot
    -0.56
    idee
    -0.52
    Must
    -0.51
     unwanted
    -0.51
     Occasionally
    -0.51
     Transparent
    -0.50
     nuance
    -0.50
    POSITIVE LOGITS
     plus
    0.64
     powerful
    0.60
     Verfügung
    0.59
    加上
    0.58
    再加上
    0.55
    bootstrapcdn
    0.55
     capable
    0.54
    المشاركات
    0.54
     potent
    0.53
     factor
    0.52
    Activations Density 0.344%

    No Known Activations