© 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. 8332
    Prev
    Next
    INDEX
    Explanations

    references to filmmaking challenges and production constraints

    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
    enschappelijke
    -0.40
     defaultstate
    -0.39
     poffible
    -0.38
    新たに
    -0.36
    exitRule
    -0.36
     fubject
    -0.36
    AsUp
    -0.36
    oznam
    -0.35
    testens
    -0.34
    лактика
    -0.34
    POSITIVE LOGITS
     very
    2.52
     quite
    1.95
     VERY
    1.94
     extremely
    1.93
     очень
    1.91
    very
    1.89
     sehr
    1.87
     bardzo
    1.84
     muy
    1.82
    Very
    1.81
    Activations Density 2.206%

    No Known Activations