© 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. 14-GEMMASCOPE-RES-16K
    6. 2680
    Prev
    Next
    INDEX
    Explanations

    technical terms and constraints related to system performance and limitations

    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
     entregó
    -0.57
    ExtendWith
    -0.56
     protoimpl
    -0.54
     crochê
    -0.53
    Charged
    -0.51
     wikipagina
    -0.50
     recibirá
    -0.50
     apresentado
    -0.49
     fieltro
    -0.48
     sabbia
    -0.48
    POSITIVE LOGITS
     limitation
    0.75
     limitations
    0.72
    ModelAdmin
    0.64
     LIMITATIONS
    0.64
     Limitations
    0.62
    onViewCreated
    0.60
     Limitation
    0.59
    PerformLayout
    0.59
    Limitation
    0.59
     limit
    0.59
    Activations Density 0.557%

    No Known Activations