© 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. 8340
    Prev
    Next
    INDEX
    Explanations

    references to medications and their potential interactions or side effects

    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
     anthropogenic
    -0.61
    istocene
    -0.56
     hegemony
    -0.54
     vicissitudes
    -0.53
     CreateTagHelper
    -0.53
     promulgated
    -0.52
     perusal
    -0.51
    CloseOperation
    -0.51
     annum
    -0.50
     plethora
    -0.50
    POSITIVE LOGITS
     itſelf
    0.61
    Trusted
    0.49
     ſever
    0.46
     ſmall
    0.46
     perfons
    0.44
     perſon
    0.43
     your
    0.43
     Your
    0.41
    Your
    0.41
     occaf
    0.40
    Activations Density 0.496%

    No Known Activations