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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 843
    Prev
    Next
    INDEX
    Explanations

    references to racing events and participants' accomplishments in motorsport

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

    references to Formula 1 racing careers and driver biographical details.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.77
     Taktlose
    -0.63
    :✨
    -0.62
     resourceCulture
    -0.60
     Administrativna
    -0.57
    RegistryLite
    -0.56
    UnusedPrivate
    -0.54
    GEBURTSDATUM
    -0.53
    oneofs
    -0.52
    Personendaten
    -0.52
    POSITIVE LOGITS
     racing
    1.02
     race
    0.98
     Racing
    0.88
     racers
    0.86
     raced
    0.85
     races
    0.83
     racer
    0.83
    Racing
    0.80
    racing
    0.77
     Race
    0.75
    Activations Density 0.248%

    No Known Activations