© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4391
    Prev
    Next
    INDEX
    Explanations

    details related to specific vehicle models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.63
    GEBURTSDATUM
    -0.62
     defStyleAttr
    -0.59
    UnsafeEnabled
    -0.55
    StoryboardSegue
    -0.55
    TargetException
    -0.52
     Dade
    -0.50
     defStyle
    -0.50
    DockStyle
    -0.50
    enderror
    -0.50
    POSITIVE LOGITS
     Toyota
    0.87
    Toyota
    0.84
     toyota
    0.73
     Corolla
    0.68
     Camry
    0.68
     TOY
    0.66
     Prius
    0.66
     トヨタ
    0.65
    トヨタ
    0.65
    toyota
    0.64
    Activations Density 0.194%

    No Known Activations