© 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. 22-GEMMASCOPE-RES-16K
    6. 8497
    Prev
    Next
    INDEX
    Explanations

    technical details about astronomical instruments and observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Telescopes and astronomical observation

    np_acts-logits-general · gemini-2.0-flash

    observing with telescopes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.60
    RectangleBorder
    -0.55
    ftagPool
    -0.49
     plexus
    -0.47
     gela
    -0.45
    Transkript
    -0.44
     boucles
    -0.43
     stunt
    -0.43
     Tuck
    -0.43
    embal
    -0.42
    POSITIVE LOGITS
     observing
    1.08
     Observing
    1.04
     observatory
    0.98
    Observ
    0.96
     observ
    0.92
    observ
    0.92
     telescope
    0.90
     Observatory
    0.87
     observation
    0.86
     observations
    0.86
    Activations Density 0.424%

    No Known Activations