© 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. 33-GEMMASCOPE-RES-16K
    11. 10908
    Prev
    Next
    INDEX
    Explanations

    phrases describing statistical analyses or relationships in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrNull
    -0.40
     فريبيس
    -0.40
     faisant
    -0.40
    níků
    -0.39
    preced
    -0.38
    uitable
    -0.38
    occurring
    -0.37
    EnableWeb
    -0.37
    WithError
    -0.37
     preceding
    -0.36
    POSITIVE LOGITS
     represented
    0.85
     expressed
    0.80
     defined
    0.72
     assessed
    0.69
     evaluated
    0.69
     treated
    0.69
     analysed
    0.69
     obtained
    0.68
     handled
    0.68
     determined
    0.67
    Activations Density 1.235%

    No Known Activations