© 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. 25-GEMMASCOPE-RES-16K
    6. 10850
    Prev
    Next
    INDEX
    Explanations

    terms related to automotive diagnostic systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.61
     بيها
    -0.59
    ArrowToggle
    -0.57
    ScopeManager
    -0.54
    Oneof
    -0.53
     Rè
    -0.52
     '\\;'
    -0.51
    mergeFrom
    -0.51
    getProject
    -0.51
    SourceChecksum
    -0.49
    POSITIVE LOGITS
     codes
    0.90
     code
    0.81
     DTC
    0.76
     OBD
    0.75
    codes
    0.72
     ECM
    0.72
     ECU
    0.72
     PCM
    0.71
     ecu
    0.70
     coding
    0.69
    Activations Density 0.227%

    No Known Activations