© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 11371
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of observing or noting phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     P
    -0.69
    P
    -0.68
     A
    -0.59
    retty
    -0.57
    wyn
    -0.57
    nu
    -0.57
     Brittany
    -0.55
     It
    -0.55
     Dillon
    -0.55
     tiver
    -0.54
    POSITIVE LOGITS
    observations
    1.54
     observations
    1.53
     obser
    1.50
     Observation
    1.50
     Observations
    1.50
     OBSERV
    1.48
     observation
    1.47
     observes
    1.47
     observe
    1.43
     Observed
    1.42
    Activations Density 0.105%

    No Known Activations