© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2396
    Prev
    Next
    INDEX
    Explanations

    references to partnerships and collaborative relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    snowy
    -0.75
    Hockey
    -0.74
     fatig
    -0.72
     Hockey
    -0.71
     srs
    -0.69
    ientôt
    -0.68
     Kej
    -0.68
     Nok
    -0.68
     Scin
    -0.67
     Yag
    -0.67
    POSITIVE LOGITS
     partners
    1.79
     Partners
    1.70
    Partners
    1.67
     partner
    1.65
     Partner
    1.63
    partners
    1.63
     PARTNER
    1.52
    Partner
    1.51
     PARTNERS
    1.48
    partner
    1.45
    Activations Density 0.039%

    No Known Activations