© 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. 18-GEMMASCOPE-RES-16K
    11. 1658
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to cases and rulings

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

    preceding an issue, statement, or transaction

    np_acts-logits-general · gemini-2.0-flash

    legal and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.99
    ſelves
    -0.97
     purpoſe
    -0.96
     pleaſure
    -0.94
     ſtate
    -0.88
     myſelf
    -0.85
    ніципалі
    -0.84
    IntoConstraints
    -0.84
     fevere
    -0.81
     houſe
    -0.80
    POSITIVE LOGITS
     theory
    0.73
     concept
    0.68
     study
    0.66
     list
    0.63
     policy
    0.63
     analysis
    0.63
     category
    0.61
     program
    0.58
     statement
    0.58
     research
    0.58
    Activations Density 1.175%

    No Known Activations