Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2174
    Prev
    Next
    INDEX
    Explanations

    financial terms related to contracts and payments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "the" in legal or formal documents

    np_acts-logits-general · gemini-2.0-flash

    legal or conditional clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.64
     strangely
    -0.55
     huge
    -0.55
     famously
    -0.55
     gyhoeddwyd
    -0.55
     seems
    -0.52
     eher
    -0.51
     weirdly
    -0.50
     tricky
    -0.50
     barely
    -0.48
    POSITIVE LOGITS
     foregoing
    1.11
     aforesaid
    0.96
     applicable
    0.90
     above
    0.85
     undersigned
    0.82
    above
    0.82
     provisions
    0.81
     jScrollPane
    0.81
    applicable
    0.81
     herein
    0.81
    Activations Density 0.865%

    No Known Activations