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. 22-GEMMASCOPE-RES-16K
    6. 16269
    Prev
    Next
    INDEX
    Explanations

    technical terms related to automotive mechanisms and lubricants

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

    Automotive or mechanical components

    np_acts-logits-general · gemini-2.0-flash

    automotive mechanics and parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ericsson
    -0.56
    ridescent
    -0.55
     eddy
    -0.55
     Schneider
    -0.54
    ModelAdmin
    -0.54
    ∬
    -0.53
     AssemblyCompany
    -0.50
     varnish
    -0.49
    conda
    -0.49
    Gill
    -0.49
    POSITIVE LOGITS
     axle
    0.72
     Axle
    0.64
     axles
    0.64
    axle
    0.61
     front
    0.61
     steering
    0.59
     LCA
    0.57
     pinion
    0.56
    Front
    0.55
    steering
    0.54
    Activations Density 0.180%

    No Known Activations