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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15866
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific references to individuals in racing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.52
     caminhada
    -0.42
     HttpNotFound
    -0.41
    tonsoft
    -0.41
     MainAxisSize
    -0.40
    TargetApi
    -0.38
     missione
    -0.36
    WarningLevel
    -0.36
     trône
    -0.36
    Geografia
    -0.36
    POSITIVE LOGITS
     race
    2.36
     racing
    2.27
     races
    2.09
     racers
    2.05
     Race
    1.98
     racer
    1.91
     raced
    1.90
    Race
    1.90
    race
    1.87
    racing
    1.84
    Activations Density 0.402%

    No Known Activations