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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1425
    Prev
    Next
    INDEX
    Explanations

    instructions related to brake maintenance and pad replacement

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

    "brake" and related terms

    np_acts-logits-general · gemini-2.0-flash

    brake pads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.56
    FormTagHelper
    -0.51
     Enumeration
    -0.51
    Constru
    -0.49
     levan
    -0.48
     Ellington
    -0.47
     Beale
    -0.47
     Soriano
    -0.47
    ünstig
    -0.47
    ništ
    -0.47
    POSITIVE LOGITS
     brake
    1.36
     brakes
    1.30
     braking
    1.24
     Brake
    1.22
    brake
    1.19
     Brakes
    1.16
    Brake
    1.12
     pads
    0.94
     Brems
    0.93
     calipers
    0.87
    Activations Density 0.153%

    No Known Activations