© 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. 8433
    Prev
    Next
    INDEX
    Explanations

    keywords associated with data processing and serialization in programming 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
     pleaſure
    -0.69
     houſe
    -0.66
     surla
    -0.63
    antaranya
    -0.59
     leſs
    -0.57
     ſche
    -0.56
     fevere
    -0.56
    ſelves
    -0.55
     ſtate
    -0.55
     reaſon
    -0.54
    POSITIVE LOGITS
    ness
    0.53
    isContained
    0.50
    irected
    0.50
    ded
    0.44
     gepubliceerd
    0.39
    s
    0.39
     United
    0.38
     Measured
    0.38
     Owned
    0.38
    ted
    0.38
    Activations Density 1.435%

    No Known Activations