© 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. 18-GEMMASCOPE-RES-16K
    6. 2186
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and structures in nano-scale materials

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

    Vibrational or resonant "modes"

    np_acts-logits-general · gemini-2.0-flash

    modes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    libft
    -0.58
    addCriterion
    -0.56
    jsdelivr
    -0.53
     moeite
    -0.53
     Selamat
    -0.51
    ueuse
    -0.50
    تقاوى
    -0.49
     sahabat
    -0.49
    friendship
    -0.49
     friendship
    -0.49
    POSITIVE LOGITS
     modes
    0.98
     Modes
    0.84
    modes
    0.83
     vibrations
    0.78
     modos
    0.75
    Modes
    0.75
     resonances
    0.74
     mode
    0.73
     resonance
    0.72
     vibration
    0.68
    Activations Density 0.826%

    No Known Activations