© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8588
    Prev
    Next
    INDEX
    Explanations

    references to brake pads and their maintenance or replacement

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

    before "pad" or related to "brake"

    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 @ 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
    <?
    -0.68
    ftagPool
    -0.63
     FetchType
    -0.62
     Beale
    -0.55
    createCanvas
    -0.54
    CodedInputStream
    -0.52
    Draft
    -0.52
    цтва
    -0.48
    InSection
    -0.48
     crossorigin
    -0.48
    POSITIVE LOGITS
     brake
    1.16
     brakes
    1.06
     Brake
    1.01
     braking
    1.00
     disc
    0.98
     calipers
    0.96
     discs
    0.95
    brake
    0.95
    Brake
    0.94
     caliper
    0.94
    Activations Density 0.143%

    No Known Activations