© 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. 6-GEMMASCOPE-RES-16K
    11. 3788
    Prev
    Next
    INDEX
    Explanations

    terms related to initiating, triggering, or causing specific actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vibr
    -0.71
    ContentAlignment
    -0.70
    Rés
    -0.68
     Darn
    -0.68
    Wes
    -0.67
     &[
    -0.67
     OW
    -0.67
     Scu
    -0.67
    stru
    -0.66
     Basi
    -0.65
    POSITIVE LOGITS
     triggered
    1.21
     оригіналу
    1.16
    initiate
    1.15
     trigger
    1.07
     initiate
    1.07
     déclen
    1.04
    initiated
    1.04
    triggered
    1.03
     initiated
    1.02
    induced
    1.01
    Activations Density 0.222%

    No Known Activations