© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5354
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'observe' and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    templateUrl
    -0.69
    SequentialGroup
    -0.64
    躇
    -0.62
     Dalton
    -0.59
    kyl
    -0.58
    を増
    -0.56
     pinggang
    -0.54
     sou
    -0.53
    enken
    -0.52
     Brittany
    -0.52
    POSITIVE LOGITS
     observe
    3.07
     observation
    2.90
     observed
    2.88
     observes
    2.86
     observing
    2.82
     Observe
    2.79
     OBSERV
    2.75
     Observation
    2.68
     Observed
    2.66
    observe
    2.66
    Activations Density 0.046%

    No Known Activations