© 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. 8-GEMMASCOPE-RES-16K
    11. 14780
    Prev
    Next
    INDEX
    Explanations

    medical terminology and details related to healthcare processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favors
    -0.82
    Rohy
    -0.82
     OSHA
    -0.77
     parlor
    -0.77
     theaters
    -0.77
    Neighbors
    -0.76
     ivelany
    -0.74
     odors
    -0.72
     favorably
    -0.72
     Neighbors
    -0.71
    POSITIVE LOGITS
    Whilst
    1.39
     realised
    1.38
     Whilst
    1.37
     specialises
    1.34
    initialise
    1.33
     realise
    1.32
     tyres
    1.30
    behaviour
    1.30
     specialising
    1.29
     realises
    1.29
    Activations Density 1.711%

    No Known Activations