© 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. 3504
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize clarity and understanding in legal contexts

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

    Tokens preceding "clear."

    np_acts-logits-general · gemini-2.0-flash

    making clear

    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
     surface
    -1.07
     Surface
    -1.02
    Surface
    -1.01
     SURFACE
    -0.98
    surface
    -0.94
     surfacing
    -0.81
     superficie
    -0.80
     oppervlak
    -0.78
    SURFACE
    -0.77
     surfaces
    -0.77
    POSITIVE LOGITS
     clear
    1.65
    clear
    1.42
     CLEAR
    1.36
     clearly
    1.29
     Clear
    1.28
    Clear
    1.27
    CLEAR
    1.21
     clarify
    1.13
     clarity
    1.13
     duidelijk
    1.12
    Activations Density 0.282%

    No Known Activations