© 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. 1-GEMMASCOPE-RES-16K
    11. 6802
    Prev
    Next
    INDEX
    Explanations

    terms related to industrial contexts and applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.78
     Johnson
    -0.67
    Johnson
    -0.65
     JOHNSON
    -0.65
     johnson
    -0.65
     vetorial
    -0.55
    mgr
    -0.54
     flé
    -0.53
     Zanzibar
    -0.53
     Mange
    -0.53
    POSITIVE LOGITS
     Industrial
    2.01
     industrial
    2.01
    Industrial
    1.94
    industrial
    1.89
     INDUSTRIAL
    1.79
    INDUSTR
    1.31
     industriale
    1.30
     industriales
    1.29
     industrielle
    1.19
     industri
    1.16
    Activations Density 0.065%

    No Known Activations